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. 24149
    Prev
    Next
    INDEX
    Explanations

    terms related to coordination, regulation, manipulation, duplication, and negotiation in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to structural organization and control processes

    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
    estones
    -0.75
    rop
    -0.71
    otrop
    -0.70
    bold
    -0.66
    ahon
    -0.66
    robe
    -0.66
    gets
    -0.63
    eva
    -0.63
    enced
    -0.62
    igmatic
    -0.62
    POSITIVE LOGITS
    ary
    0.92
    xual
    0.88
    alist
    0.85
     thereof
    0.79
    ist
    0.79
    ISM
    0.78
    avascript
    0.78
     process
    0.75
    naire
    0.75
     technique
    0.73
    Activations Density 0.147%

    No Known Activations