Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7011
    Prev
    Next
    INDEX
    Explanations

    rests between quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating loss or being lost

    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
     shopping
    -0.64
    cler
    -0.62
     demolition
    -0.59
     green
    -0.59
     eviction
    -0.59
     Bhar
    -0.58
     div
    -0.58
     ready
    -0.58
     clause
    -0.58
     el
    -0.58
    POSITIVE LOGITS
    OST
    4.49
    ost
    1.41
    ONEY
    1.37
    OOK
    1.28
    OTOS
    1.25
    UST
    1.24
    OSE
    1.23
    OSS
    1.19
    AST
    1.19
    oster
    1.16
    Activations Density 0.014%

    No Known Activations