© 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. 23365
    Prev
    Next
    INDEX
    Explanations

    verbs indicating an action or decision is being made by a group or entity

    oai_token-act-pair · gpt-3.5-turbo

    negative statements and skepticism regarding other people's actions or intentions

    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
    accompanied
    -0.76
    isal
    -0.70
    foreseen
    -0.63
    Pass
    -0.62
    fters
    -0.60
    was
    -0.59
    critical
    -0.59
    ommel
    -0.57
    itaire
    -0.57
    worth
    -0.57
    POSITIVE LOGITS
     themselves
    1.27
    selves
    0.96
     selves
    0.92
     microphones
    0.74
     jointly
    0.72
     helmets
    0.70
     uniforms
    0.69
     THEIR
    0.68
     yourselves
    0.67
    ovie
    0.65
    Activations Density 0.771%

    No Known Activations