© 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. 4-RES-JB
    11. 261
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules or restrictions, often starting with 'no-'

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to negation or absence

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

    No Comments

    Negative Logits
     Fork
    -0.75
    ãĥ¼ãĥĨãĤ£
    -0.75
     Reloaded
    -0.75
    çĶ°
    -0.72
     Strait
    -0.71
     Kuh
    -0.67
     Lod
    -0.64
     LIN
    -0.64
    Ń·
    -0.63
     Cannon
    -0.63
    POSITIVE LOGITS
    sized
    1.03
     whatsoever
    1.02
    scale
    0.97
    reply
    0.96
    minded
    0.95
    zero
    0.94
    repeat
    0.93
    degree
    0.90
    level
    0.89
    government
    0.89
    Activations Density 0.042%

    No Known Activations