© 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. 16873
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "PICK"

    oai_token-act-pair · gpt-3.5-turbo

    words related to financial transactions and money management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    atron
    -0.93
    hex
    -0.92
    ithe
    -0.88
    omorph
    -0.88
    acent
    -0.87
    iform
    -0.87
    cha
    -0.87
    ials
    -0.86
    adic
    -0.86
    fal
    -0.86
    POSITIVE LOGITS
    ICK
    2.18
    ANK
    2.00
    OUT
    1.98
    ISE
    1.98
    ONY
    1.96
    ICH
    1.94
    ERE
    1.93
    UNE
    1.92
    ANT
    1.91
    ALLY
    1.91
    Activations Density 0.081%

    No Known Activations