© 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. 0-RES-JB
    11. 16550
    Prev
    Next
    INDEX
    Explanations

    references to someone or something named "Monty."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ///
    -0.70
    ubi
    -0.70
     sig
    -0.68
    IFT
    -0.67
    SH
    -0.67
     FIR
    -0.67
    FACE
    -0.65
    Kin
    -0.65
    SHIP
    -0.64
    ADRA
    -0.64
    POSITIVE LOGITS
     Mont
    3.63
    Mont
    2.66
     mont
    1.65
    mont
    1.45
     Monte
    1.39
     Qué
    1.34
     Montana
    1.31
     Montgomery
    1.30
     Monteneg
    1.26
     Monaco
    1.22
    Activations Density 0.019%

    No Known Activations