Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4209
    Prev
    Next
    INDEX
    Explanations

    verbs indicating achievement or successful outcomes

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "managed to" along with actions following it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Respons
    -0.75
     Actions
    -0.71
     Explan
    -0.71
    prem
    -0.71
    Sold
    -0.70
    LES
    -0.69
     Forward
    -0.69
     Perspect
    -0.68
     Closing
    -0.67
    backs
    -0.67
    POSITIVE LOGITS
     convince
    1.32
     overcome
    1.29
     achieve
    1.27
     evade
    1.26
     survive
    1.25
     accomplish
    1.22
     penetrate
    1.20
     infiltrate
    1.18
     get
    1.11
     circumvent
    1.11
    Activations Density 0.078%

    No Known Activations