© 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. 7484
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "if" and referring to actions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "it" and its context in various statements

    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
    UTC
    -0.71
     Penny
    -0.71
    OTOS
    -0.70
     Clause
    -0.66
     Tooth
    -0.66
    UFF
    -0.65
    Offline
    -0.63
    ¿½
    -0.60
    Ŀ
    -0.60
     Sight
    -0.60
    POSITIVE LOGITS
    'll
    1.22
    'd
    0.98
     shouldn
    0.91
     certainly
    0.91
     ought
    0.89
     SHOULD
    0.88
    're
    0.87
     probably
    0.87
     surely
    0.87
     MUST
    0.85
    Activations Density 0.178%

    No Known Activations