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. 24208
    Prev
    Next
    INDEX
    Explanations

    phrases related to the future or progression over time

    oai_token-act-pair · gpt-3.5-turbo

    references to 'the road' in various contexts

    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
    emort
    -0.87
     Socket
    -0.74
    abilia
    -0.70
    ermott
    -0.70
    ancial
    -0.69
    achusetts
    -0.68
    encies
    -0.68
    teness
    -0.68
    Dat
    -0.67
    andum
    -0.67
    POSITIVE LOGITS
    trip
    0.98
    lane
    0.86
    block
    0.84
    ways
    0.83
    cycle
    0.82
    runner
    0.80
    fare
    0.78
    side
    0.78
     road
    0.76
    blocks
    0.76
    Activations Density 0.014%

    No Known Activations