© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23511
    Prev
    Next
    INDEX
    Explanations

    phrases related to hypothetical scenarios and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases or expressions of possibility

    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
    foreseen
    -0.64
    ZI
    -0.63
    igma
    -0.63
    pires
    -0.61
    Tumblr
    -0.60
    reality
    -0.60
    ansas
    -0.59
    itis
    -0.59
    engineering
    -0.59
     trendy
    -0.58
    POSITIVE LOGITS
     be
    1.09
     also
    0.99
     derive
    0.95
     introduce
    0.95
     arrive
    0.94
     create
    0.93
     incorporate
    0.92
     divert
    0.91
     propose
    0.90
     doubtless
    0.89
    Activations Density 0.295%

    No Known Activations