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. 7411
    Prev
    Next
    INDEX
    Explanations

    verbs related to achievement or accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    verbs and auxiliary verbs indicating actions or states of being 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
     zo
    -0.71
     Ago
    -0.70
     Lun
    -0.69
     Awakens
    -0.67
     Sol
    -0.67
     Kron
    -0.64
     Aer
    -0.63
     Shal
    -0.61
     bond
    -0.61
     Ital
    -0.61
    POSITIVE LOGITS
     somehow
    0.89
     indistinguishable
    0.82
    Ͻ
    0.79
     disproportionately
    0.78
    entimes
    0.76
     inex
    0.74
    ŃĶ
    0.73
    çͰ
    0.71
     inevitably
    0.71
     outwe
    0.70
    Activations Density 0.928%

    No Known Activations