© 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. 2-RES-JB
    11. 3866
    Prev
    Next
    INDEX
    Explanations

    words related to signaling or guiding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to guiding lights or signals

    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
    ivan
    -0.85
    edi
    -0.73
    ulu
    -0.73
    ordan
    -0.72
    ryu
    -0.70
    ammad
    -0.69
    MI
    -0.69
    essee
    -0.69
    dos
    -0.67
    itals
    -0.67
    POSITIVE LOGITS
     beacon
    1.24
     Beacon
    0.88
     Cyn
    0.78
    pole
    0.77
     bom
    0.73
     transmitter
    0.73
    ãĤ¤ãĥĪ
    0.70
     bracelet
    0.70
     markers
    0.70
    ically
    0.70
    Activations Density 0.008%

    No Known Activations