© 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. 7-RES-JB
    11. 21451
    Prev
    Next
    INDEX
    Explanations

    specific days and times mentioned in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    scheduled broadcast times for television programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?).
    -0.89
    )).
    -0.82
    .).
    -0.80
    }.
    -0.78
    ]).
    -0.77
    ?".
    -0.77
    .</
    -0.77
    ]."
    -0.72
     thereof
    -0.70
    $.
    -0.70
    POSITIVE LOGITS
    anchester
    0.54
    resa
    0.51
     Guan
    0.47
     Kaplan
    0.46
     Gw
    0.46
    undy
    0.46
     Sharif
    0.45
     Canterbury
    0.45
     Brunswick
    0.45
     divided
    0.45
    Activations Density 1.832%

    No Known Activations