© 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. 17116
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events happening

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to potential consequences or outcomes of actions

    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
     âĢ
    -0.55
    âĢ
    -0.51
     facult
    -0.49
     interns
    -0.49
     Abbott
    -0.47
     hig
    -0.47
     skelet
    -0.46
     derog
    -0.45
     appell
    -0.45
     menstru
    -0.44
    POSITIVE LOGITS
    instead
    0.55
     forever
    0.53
     instead
    0.53
    ever
    0.52
    oming
    0.52
    !]
    0.51
    now
    0.51
     immediately
    0.50
    destroy
    0.50
    ossible
    0.50
    Activations Density 1.442%

    No Known Activations