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. 8-RES-JB
    6. 14772
    Prev
    Next
    INDEX
    Explanations

    sentences with emphatic or declarative statements

    oai_token-act-pair · gpt-3.5-turbo

    symbols or special characters used in unusual or unconventional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ©
    -0.72
     0004
    -0.58
    ModLoader
    -0.58
     guiActiveUnfocused
    -0.56
    ccording
    -0.54
    pei
    -0.54
    iard
    -0.54
    ousel
    -0.53
     Slug
    -0.52
    ...]
    -0.52
    POSITIVE LOGITS
    especially
    1.20
    perhaps
    1.17
    particularly
    1.15
    albeit
    1.14
     namely
    1.13
    although
    1.11
    except
    1.02
    they
    1.01
    _-
    1.01
    something
    0.98
    Activations Density 0.153%

    No Known Activations