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. 3680
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations and political events

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and regions

    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
    apego
    -0.56
     Flavoring
    -0.49
    orsi
    -0.46
    ulner
    -0.46
    Tags
    -0.44
    abilia
    -0.44
     passwords
    -0.44
    vantage
    -0.43
    onite
    -0.43
    henko
    -0.43
    POSITIVE LOGITS
     vicinity
    0.83
     guise
    0.81
     circles
    0.66
     midst
    0.63
     manner
    0.60
     periphery
    0.60
     Indies
    0.60
     countryside
    0.58
     context
    0.58
     courtyard
    0.56
    Activations Density 0.898%

    No Known Activations