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. 2694
    Prev
    Next
    INDEX
    Explanations

    references to financial analysts and their opinions or comments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of analysts and their commentary or predictions related to various subjects

    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
    boats
    -0.70
     traumatic
    -0.66
     Tub
    -0.66
     raft
    -0.63
    frey
    -0.63
    boat
    -0.61
     Mamm
    -0.61
    foot
    -0.60
     Cha
    -0.60
     DeL
    -0.59
    POSITIVE LOGITS
     analyst
    1.14
    alyst
    1.09
     analysts
    0.89
     Analyst
    0.82
    rador
    0.79
    sonian
    0.78
    igible
    0.75
    aturday
    0.73
    Analy
    0.72
    onite
    0.72
    Activations Density 0.027%

    No Known Activations