© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 724
    Prev
    Next
    INDEX
    Explanations

    the term "rookie"

    oai_token-act-pair · gpt-4-turbo

    mentions of rookie players in sports contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to rookie players in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alia
    -0.92
    choes
    -0.87
    ombat
    -0.86
    uria
    -0.81
    akespe
    -0.80
    atche
    -0.78
    illance
    -0.77
    arf
    -0.77
    cemic
    -0.75
    fact
    -0.75
    POSITIVE LOGITS
     rookies
    0.96
     rookie
    0.89
     Scouting
    0.85
     Rookie
    0.70
    bies
    0.70
    Kings
    0.68
    2019
    0.66
     quarterbacks
    0.64
    ãĥ£
    0.64
    smanship
    0.63
    Activations Density 0.011%

    No Known Activations