© 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. 4-RES-JB
    11. 14773
    Prev
    Next
    INDEX
    Explanations

    names related to Boyle

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and specific teams in a sports context

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

    No Comments

    Negative Logits
    eering
    -0.87
    eanor
    -0.84
    uador
    -0.81
    urated
    -0.81
    ITNESS
    -0.78
    ansas
    -0.76
    azeera
    -0.75
     oun
    -0.72
    urities
    -0.72
    ipel
    -0.71
    POSITIVE LOGITS
     Bruins
    0.86
     Boh
    0.81
     Brah
    0.72
    hood
    0.71
     Ruk
    0.69
    oslov
    0.68
    etooth
    0.66
    zag
    0.65
    Mos
    0.65
     Bru
    0.64
    Activations Density 0.014%

    No Known Activations