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. 12489
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographic locations and surroundings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to geographical locations and their descriptions

    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
     fueling
    -0.82
     fueled
    -0.81
     GoPro
    -0.80
    Based
    -0.80
     trending
    -0.80
     Dynamics
    -0.78
     targeted
    -0.77
     targeting
    -0.77
    SAN
    -0.77
    Ops
    -0.77
    POSITIVE LOGITS
    ,—
    1.23
     thence
    1.19
     negro
    1.12
     splend
    1.08
     labou
    1.00
     consec
    0.99
     splendid
    0.98
     pious
    0.97
     brill
    0.95
     nearer
    0.95
    Activations Density 1.203%

    No Known Activations