© 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. 8-RES-JB
    11. 15113
    Prev
    Next
    INDEX
    Explanations

    age of individuals from the text

    oai_token-act-pair · gpt-3.5-turbo

    numerical age indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prise
    -0.62
     diversion
    -0.62
     signage
    -0.61
     locality
    -0.61
     overhead
    -0.60
     retali
    -0.60
    elist
    -0.59
     disturbance
    -0.59
     derog
    -0.59
     repr
    -0.58
    POSITIVE LOGITS
    years
    1.03
    ½
    1.02
     years
    1.01
    yrs
    0.93
     mph
    0.88
    mph
    0.88
    cm
    0.87
    lbs
    0.85
    %.
    0.85
    yo
    0.82
    Activations Density 0.092%

    No Known Activations