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. 10513
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographical locations, especially "Tall" as it appears in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific geographical location, particularly "Tall" and "Eston."

    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
    çĦ
    -0.70
     mileage
    -0.69
     indifferent
    -0.68
    OUP
    -0.64
    gnu
    -0.63
    èĢ
    -0.63
    tumblr
    -0.62
    çīĪ
    -0.61
    è»
    -0.60
    åº
    -0.60
    POSITIVE LOGITS
    alion
    1.12
    arus
    1.01
    iago
    0.94
    mouth
    0.94
    itude
    0.90
     Tall
    0.86
    ewitness
    0.85
    izard
    0.83
    ewater
    0.83
    ogether
    0.82
    Activations Density 0.021%

    No Known Activations