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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 7304
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to inhabiting a place or environment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to living beings or entities that occupy a place

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

    No Comments

    Negative Logits
    heet
    -0.82
    MED
    -0.79
    ripp
    -0.78
    iem
    -0.69
    printed
    -0.67
    TPS
    -0.66
    TER
    -0.64
    jab
    -0.64
    rah
    -0.64
    med
    -0.64
    POSITIVE LOGITS
     inhabit
    0.92
     inhab
    0.85
    uria
    0.81
     inhabited
    0.78
    ants
    0.76
    ocations
    0.75
    izen
    0.73
     inhabitants
    0.72
    izabeth
    0.71
     dwell
    0.71
    Activations Density 0.021%

    No Known Activations