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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21996
    Prev
    Next
    INDEX
    Explanations

    words related to causing a change or reaction in a physical or biological system

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of induction and its various applications or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fman
    -0.70
    dain
    -0.70
    foundation
    -0.69
    lain
    -0.69
    neau
    -0.68
     motto
    -0.66
    esides
    -0.65
    sonian
    -0.64
    Ü
    -0.64
     Pound
    -0.63
    POSITIVE LOGITS
     plur
    0.95
     induced
    0.92
     inducing
    0.88
     apopt
    0.88
    ocy
    0.85
     induce
    0.84
     induces
    0.83
     analges
    0.82
    orescence
    0.82
     hallucinations
    0.81
    Activations Density 0.027%

    No Known Activations