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. 24072
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to a strong and positive reaction or endorsement

    oai_token-act-pair · gpt-3.5-turbo

    words related to a strong gain or increase

    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
     digitally
    -0.66
     Fin
    -0.65
     Lap
    -0.63
     Leg
    -0.63
     Met
    -0.61
     chrom
    -0.61
     migrated
    -0.61
     transm
    -0.60
     Comm
    -0.59
     Fish
    -0.59
    POSITIVE LOGITS
    ounding
    4.62
    ounded
    2.83
    ounds
    2.39
    ound
    2.14
    OUND
    1.97
    olute
    1.12
    umping
    1.07
    arming
    1.03
    ooting
    1.02
    etting
    1.01
    Activations Density 0.004%

    No Known Activations