Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 5726
    Prev
    Next
    INDEX
    Explanations

    entrances to different locations

    oai_token-act-pair · gpt-3.5-turbo

    references to entrances and exits of locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amera
    -0.72
    rior
    -0.69
    nian
    -0.66
    yan
    -0.65
    irit
    -0.64
    ilot
    -0.64
    grave
    -0.63
    die
    -0.61
    zsche
    -0.61
    riter
    -0.61
    POSITIVE LOGITS
    prise
    1.06
     thereto
    0.99
    prises
    0.88
    tainment
    0.83
     entrance
    0.83
    ways
    0.82
     portals
    0.80
     pupil
    0.80
    ococ
    0.79
     gates
    0.77
    Activations Density 0.019%

    No Known Activations