© 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. 3-RES-JB
    11. 10780
    Prev
    Next
    INDEX
    Explanations

    instances of rocky terrains or surfaces

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to rugged or challenging terrain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abetic
    -0.97
    endment
    -0.97
    umers
    -0.83
    reme
    -0.82
    abetes
    -0.77
    ulhu
    -0.76
    rity
    -0.76
    Aust
    -0.76
    ership
    -0.75
    urg
    -0.75
    POSITIVE LOGITS
     rocky
    1.02
     shores
    0.91
     volcanic
    0.83
     paths
    0.79
    lake
    0.77
     reefs
    0.77
     traject
    0.77
     islands
    0.76
     sailing
    0.76
     shore
    0.76
    Activations Density 0.010%

    No Known Activations