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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 20702
    Prev
    Next
    INDEX
    Explanations

    words related to measuring or determining something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "meter" in various contexts

    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
    ĸļ
    -0.95
    BuyableInstoreAndOnline
    -0.74
    ħĭ
    -0.74
    iesel
    -0.72
    giving
    -0.70
    GMT
    -0.69
    inventory
    -0.68
    ETF
    -0.66
    reads
    -0.65
    enthal
    -0.64
    POSITIVE LOGITS
    ministic
    1.12
    odox
    1.11
    ries
    0.92
    minist
    0.85
    pent
    0.84
    eter
    0.84
    riers
    0.83
    osexual
    0.80
    rier
    0.79
    eters
    0.79
    Activations Density 0.020%

    No Known Activations