© 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. 15160
    Prev
    Next
    INDEX
    Explanations

    text related to sports achievements and accolades

    oai_token-act-pair · gpt-3.5-turbo

    mentions of hockey player achievements and statistics

    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
     Notting
    -0.87
    istor
    -0.79
     civilisation
    -0.78
     apologise
    -0.76
     realise
    -0.69
    debian
    -0.69
     arte
    -0.69
     humour
    -0.68
     organising
    -0.67
     scept
    -0.67
    POSITIVE LOGITS
     NCAA
    1.10
     Rookie
    0.96
     undrafted
    0.93
     collegiate
    0.92
     postseason
    0.88
     Heisman
    0.86
    Atlanta
    0.85
     honorable
    0.85
     Supplemental
    0.84
    Minnesota
    0.83
    Activations Density 0.646%

    No Known Activations