© 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. 8-RES-JB
    11. 17126
    Prev
    Next
    INDEX
    Explanations

    programming languages and related terms

    oai_token-act-pair · gpt-3.5-turbo

    specific software names and terms related to technology

    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
    }.
    -0.59
    VIDIA
    -0.56
     prest
    -0.55
     reper
    -0.54
    ''.
    -0.53
    ].
    -0.53
    ".[
    -0.53
    }\
    -0.51
     ].
    -0.51
    ]."
    -0.50
    POSITIVE LOGITS
    DragonMagazine
    0.64
     directly
    0.58
     onto
    0.58
     separately
    0.57
    netflix
    0.55
    rences
    0.51
    specific
    0.51
    Pos
    0.51
    argon
    0.50
    coins
    0.50
    Activations Density 0.846%

    No Known Activations