© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 3731
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities, particularly those related to police departments or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or organization indicated by the letter 'G'

    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
    ĸļ
    -0.83
    terday
    -0.67
    oÄŁ
    -0.66
    ĺħ
    -0.64
    puter
    -0.64
     compr
    -0.63
     retrospect
    -0.62
    peer
    -0.61
     htt
    -0.60
     provision
    -0.59
    POSITIVE LOGITS
    roups
    1.25
    raphic
    1.15
    iants
    1.15
    uild
    1.10
    AMES
    1.03
    ambling
    1.03
    reetings
    1.02
    ossip
    1.01
    RAY
    1.00
    irlfriend
    1.00
    Activations Density 0.036%

    No Known Activations