© 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. 21419
    Prev
    Next
    INDEX
    Explanations

    words related to possibilities or hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and speculations about potential outcomes

    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
    lex
    -0.71
    ylon
    -0.70
    vernment
    -0.68
    ements
    -0.67
    lication
    -0.67
    endix
    -0.67
    gra
    -0.63
    onz
    -0.62
    inel
    -0.62
    ãĢı
    -0.62
    POSITIVE LOGITS
     transpired
    1.09
     happened
    1.02
     happening
    1.00
     happens
    0.97
     happen
    0.95
     happ
    0.91
     Happ
    0.82
     differe
    0.75
     ensued
    0.75
     motiv
    0.74
    Activations Density 0.133%

    No Known Activations