© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 1125
    Prev
    Next
    INDEX
    Explanations

    keywords related to items or locations that are far away or distant

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "remote" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sted
    -0.85
    stall
    -0.78
    agen
    -0.78
     Flowers
    -0.75
    ounces
    -0.73
    osterone
    -0.71
    arna
    -0.71
    ame
    -0.71
    agon
    -0.70
    rose
    -0.69
    POSITIVE LOGITS
     remote
    3.79
    remote
    2.90
     Remote
    2.60
    Remote
    2.43
     remotely
    1.76
     distant
    1.40
     rural
    1.03
     isolated
    0.92
     wireless
    0.92
     desolate
    0.89
    Activations Density 0.005%

    No Known Activations