© 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. 15154
    Prev
    Next
    INDEX
    Explanations

    terms related to liberation, freedom, and release

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to freedom and liberation

    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
    iop
    -0.70
    IDER
    -0.67
     antip
    -0.63
     McA
    -0.59
    culation
    -0.57
     similarity
    -0.56
     Nieto
    -0.56
     Integrated
    -0.55
     semic
    -0.55
     advising
    -0.55
    POSITIVE LOGITS
     hostages
    0.84
    chwitz
    0.82
     slaves
    0.80
    egu
    0.77
    bies
    0.75
     captives
    0.75
    zin
    0.75
    éĹĺ
    0.74
    selage
    0.74
    ZE
    0.73
    Activations Density 0.073%

    No Known Activations