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. 9-RES-JB
    6. 19190
    Prev
    Next
    INDEX
    Explanations

    words related to data storage devices

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "hard," indicating a focus on hardline positions or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amera
    -0.78
    umbn
    -0.74
     Tot
    -0.67
    uador
    -0.66
    ARDIS
    -0.65
    reon
    -0.64
     McCull
    -0.64
     Tyrann
    -0.63
    allery
    -0.63
    entric
    -0.62
    POSITIVE LOGITS
    coded
    1.19
    working
    1.11
    wired
    1.10
    core
    1.08
    ening
    1.05
    cover
    1.03
    ened
    1.02
    ball
    1.00
    copy
    0.93
    dri
    0.93
    Activations Density 0.036%

    No Known Activations