© 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. 17839
    Prev
    Next
    INDEX
    Explanations

    imperative verbs prompting an action

    oai_token-act-pair · gpt-3.5-turbo

    imperative or instructive verbs suggesting actions or recommendations

    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
    cffffcc
    -0.75
    mith
    -0.72
    ]=
    -0.65
    SPONSORED
    -0.62
     disg
    -0.60
    /**
    -0.58
    lt
    -0.56
    133
    -0.56
    ="/
    -0.56
    ](
    -0.55
    POSITIVE LOGITS
     Yourself
    1.18
     Your
    0.97
     Them
    0.88
     yourselves
    0.86
     yourself
    0.86
    ership
    0.85
     Quote
    0.84
    ners
    0.84
     Examples
    0.80
    ings
    0.79
    Activations Density 0.179%

    No Known Activations