© 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. 4-RES-JB
    11. 445
    Prev
    Next
    INDEX
    Explanations

    references to the possibility of different events or actions taking place

    oai_token-act-pair · gpt-3.5-turbo

    expressions of potential or hypothetical scenarios

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

    No Comments

    Negative Logits
    ogie
    -0.84
    gar
    -0.79
    ulu
    -0.76
    eye
    -0.76
    artney
    -0.75
    rix
    -0.74
    ging
    -0.74
    ilver
    -0.71
    waters
    -0.71
    gars
    -0.71
    POSITIVE LOGITS
    ossibility
    0.99
     possibility
    0.84
     confir
    0.84
     horizon
    0.76
    xual
    0.76
     unnecess
    0.76
     Rouhani
    0.75
     hypot
    0.74
     pron
    0.74
     00000000
    0.73
    Activations Density 0.015%

    No Known Activations