© 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. 10-RES-JB
    11. 7225
    Prev
    Next
    INDEX
    Explanations

    phrases related to additional information or consequences

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that indicate a continuation of thought or additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stice
    -0.71
    regate
    -0.69
    ocene
    -0.67
    ision
    -0.66
    orate
    -0.65
    urches
    -0.63
    Frames
    -0.63
    orum
    -0.63
    opoly
    -0.62
    umbledore
    -0.61
    POSITIVE LOGITS
     noteworthy
    0.99
     notable
    0.89
     implicated
    0.88
     responsible
    0.82
     applicable
    0.81
     known
    0.81
     prone
    0.78
     rumored
    0.78
     involved
    0.76
     noted
    0.76
    Activations Density 0.106%

    No Known Activations