© 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. 9-RES-JB
    11. 8593
    Prev
    Next
    INDEX
    Explanations

    conditional statements referring to hypothetical situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to hypothetical scenarios or alternate outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \\\\\\\\
    -0.78
    Topic
    -0.72
    Values
    -0.69
    fter
    -0.68
    onic
    -0.66
    Term
    -0.66
    Unless
    -0.65
     unless
    -0.65
    ãĥİ
    -0.64
    ival
    -0.64
    POSITIVE LOGITS
     intervened
    0.81
     existed
    0.73
    hin
    0.71
     jammed
    0.70
     vetoed
    0.69
     overloaded
    0.69
     hijacked
    0.67
    ided
    0.67
     raining
    0.67
     exist
    0.66
    Activations Density 0.084%

    No Known Activations