© 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. 7-RES-JB
    11. 21296
    Prev
    Next
    INDEX
    Explanations

    instances of possessive words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms related to organizations or associations

    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
    ulhu
    -0.73
    Ļ½
    -0.71
    sted
    -0.70
    ancer
    -0.70
    mented
    -0.69
    fp
    -0.68
    assian
    -0.67
    asing
    -0.66
    enza
    -0.65
    atable
    -0.65
    POSITIVE LOGITS
     own
    0.80
     collective
    0.79
     penchant
    0.75
     intentions
    0.72
     throats
    0.72
     respective
    0.71
     heads
    0.69
     insistence
    0.68
     disapproval
    0.68
     inaugural
    0.68
    Activations Density 0.035%

    No Known Activations