© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 14087
    Prev
    Next
    INDEX
    Explanations

    instances where someone has successfully achieved something or overcome a challenge

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "managed" followed by various infinitive verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.81
     Respons
    -0.77
     Actions
    -0.70
     duties
    -0.68
     Closing
    -0.68
     Continued
    -0.67
    LES
    -0.67
    ENDED
    -0.65
     Explan
    -0.64
    grounds
    -0.64
    POSITIVE LOGITS
     convince
    1.38
     achieve
    1.29
     accomplish
    1.25
     infiltrate
    1.24
     overcome
    1.23
     survive
    1.20
     muster
    1.20
     evade
    1.18
     persuade
    1.18
     penetrate
    1.17
    Activations Density 0.115%

    No Known Activations