© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17752
    Prev
    Next
    INDEX
    Explanations

    words related to exporting or trade

    oai_token-act-pair · gpt-3.5-turbo

    references to exports in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    STEM
    -0.75
     Crom
    -0.70
    WORK
    -0.69
    LOAD
    -0.68
    warm
    -0.68
     GOODMAN
    -0.68
     Luck
    -0.67
    HEAD
    -0.66
    GROUND
    -0.65
     Hook
    -0.65
    POSITIVE LOGITS
    ropri
    1.37
    orters
    1.36
    orter
    1.18
    ulsion
    1.12
    ittance
    1.06
    anse
    1.06
    onents
    1.06
    iring
    1.04
    ository
    1.03
    iry
    1.03
    Activations Density 0.027%

    No Known Activations