© 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. 11-RES-JB
    11. 18764
    Prev
    Next
    INDEX
    Explanations

    phrases indicating acceptance, understanding, or negotiation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "come to" or similar expressions indicating acceptance or realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    going
    -0.73
     flowed
    -0.63
    vich
    -0.61
    ŃĶ
    -0.61
    TION
    -0.60
    shall
    -0.60
    optional
    -0.60
     casing
    -0.59
    hur
    -0.58
    worthiness
    -0.57
    POSITIVE LOGITS
     grips
    1.51
     realise
    1.19
     terms
    1.16
     realize
    1.15
     rely
    1.06
     regret
    1.01
     blows
    1.01
     believe
    0.99
     understand
    0.98
     conclusions
    0.97
    Activations Density 0.050%

    No Known Activations