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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 24045
    Prev
    Next
    INDEX
    Explanations

    phrases describing something as difficult or resistant to change

    oai_token-act-pair · gpt-3.5-turbo

    words related to conditions of reliability and stability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ri
    -0.64
     NCT
    -0.61
     steroids
    -0.61
     rings
    -0.60
     bol
    -0.60
     CU
    -0.60
     anew
    -0.58
    uits
    -0.58
     CTR
    -0.58
    tti
    -0.57
    POSITIVE LOGITS
    able
    1.58
    ably
    1.58
    ables
    1.39
    ABLE
    1.36
    ability
    1.32
    worthy
    1.25
    ledged
    1.25
    ivable
    1.24
    ingly
    1.21
    abled
    1.20
    Activations Density 0.115%

    No Known Activations