© 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. 0-RES-JB
    11. 6872
    Prev
    Next
    INDEX
    Explanations

    references to individuals related to a specific organization or place

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups or entities, particularly focused on "emirs" and military organizations like the RAF

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boro
    -0.88
     Nieto
    -0.69
    Nit
    -0.66
    TN
    -0.65
     Cube
    -0.64
    天
    -0.64
     commodity
    -0.63
    nox
    -0.61
     Kira
    -0.59
    ENE
    -0.59
    POSITIVE LOGITS
    irs
    3.71
     RAF
    1.18
    plin
    1.14
     Fathers
    0.91
    idays
    0.88
     scalp
    0.88
    Ùħ
    0.88
    doms
    0.84
     Hamp
    0.78
     Franks
    0.76
    Activations Density 0.024%

    No Known Activations