© 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. 7453
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to limits or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating exclusion or limitations

    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
     deduction
    -0.77
     Savings
    -0.72
     aftermath
    -0.67
    iage
    -0.66
    ulhu
    -0.65
     clause
    -0.64
     DRAG
    -0.64
     SHARES
    -0.64
     Caucasus
    -0.63
     Cah
    -0.63
    POSITIVE LOGITS
    handedly
    1.13
    compatible
    1.11
    enough
    1.11
    assed
    1.10
    eligible
    1.06
    tested
    1.05
    eyed
    1.04
    sided
    1.02
    heartedly
    1.01
    focused
    1.01
    Activations Density 0.167%

    No Known Activations