© 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. 1-RES-JB
    11. 3231
    Prev
    Next
    INDEX
    Explanations

    social media or forum profile information

    oai_token-act-pair · gpt-3.5-turbo

    instances of user account or profile information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andro
    -0.85
    othy
    -0.81
    ouf
    -0.76
    agos
    -0.72
    ider
    -0.70
    atically
    -0.69
    utenberg
    -0.68
    othe
    -0.67
     streets
    -0.66
    iren
    -0.66
    POSITIVE LOGITS
     Joined
    1.57
    Joined
    0.98
     Rankings
    0.83
    76561
    0.82
    âĸ¬
    0.79
    ertodd
    0.78
    âĸ¬âĸ¬
    0.77
    pedia
    0.75
    uates
    0.71
    Offline
    0.70
    Activations Density 0.005%

    No Known Activations