© 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. 8-RES-JB
    11. 18577
    Prev
    Next
    INDEX
    Explanations

    phrases related to arriving at different locations or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to arrival locations and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.71
    rand
    -0.70
    ult
    -0.69
    rat
    -0.67
    ality
    -0.67
    criptions
    -0.64
    ens
    -0.64
    gey
    -0.63
    above
    -0.62
    rating
    -0.61
    POSITIVE LOGITS
     shores
    0.95
    INGTON
    0.81
     Arri
    0.78
     doorstep
    0.75
     Athens
    0.71
     Baghdad
    0.71
     Medina
    0.70
    eport
    0.70
     Aires
    0.69
     Alexandria
    0.69
    Activations Density 0.146%

    No Known Activations