© 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. 9-RES-JB
    11. 1485
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    oai_token-act-pair · gpt-3.5-turbo

    HTML tags and attributes

    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
     Defendant
    -0.67
     Plaintiff
    -0.60
    advertising
    -0.59
    Evil
    -0.56
    ´
    -0.55
     derogatory
    -0.53
     alot
    -0.53
    """
    -0.51
    Gate
    -0.51
     Defendants
    -0.50
    POSITIVE LOGITS
     newfound
    0.72
     renewed
    0.71
     restored
    0.69
     anew
    0.69
     recapt
    0.68
     still
    0.66
    sequent
    0.65
     nonetheless
    0.65
     revived
    0.65
     reckoning
    0.64
    Activations Density 1.618%

    No Known Activations