© 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. 2-RES-JB
    11. 12861
    Prev
    Next
    INDEX
    Explanations

    the word "house" as part of a larger entity or concept

    oai_token-act-pair · gpt-3.5-turbo

    references to various houses or buildings, particularly in a residential or organizational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DPR
    -0.84
     Archdemon
    -0.71
    istically
    -0.64
     feder
    -0.63
     concluding
    -0.62
     CNS
    -0.61
     distant
    -0.61
     timelines
    -0.60
     polar
    -0.60
     plurality
    -0.59
    POSITIVE LOGITS
    hold
    1.19
    door
    1.05
    wife
    1.01
    wives
    0.98
    warming
    0.93
    plate
    0.92
    loo
    0.91
    house
    0.91
    keeping
    0.89
    holder
    0.88
    Activations Density 0.011%

    No Known Activations