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. 19872
    Prev
    Next
    INDEX
    Explanations

    locations where people have moved to

    oai_token-act-pair · gpt-3.5-turbo

    instances of movement or relocation

    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
     downed
    -0.65
     SERV
    -0.62
     Coup
    -0.60
    icious
    -0.60
    PLIED
    -0.58
     thereof
    -0.58
     worthy
    -0.57
     ramifications
    -0.56
    ymes
    -0.55
    IJ
    -0.55
    POSITIVE LOGITS
     grips
    0.78
     accommodate
    0.75
     relocate
    0.71
     pursue
    0.70
    onds
    0.68
    oult
    0.68
     insure
    0.68
    join
    0.67
    ordes
    0.66
     eliminate
    0.66
    Activations Density 0.113%

    No Known Activations