© 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. 4-RES-JB
    11. 7620
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to technology and possibly software development

    oai_token-act-pair · gpt-3.5-turbo

    words related to acceptance and approval

    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
     challeng
    -0.78
    ailability
    -0.75
    facing
    -0.69
    dden
    -0.67
    church
    -0.67
     occasions
    -0.66
     mosqu
    -0.66
     debilitating
    -0.66
     coli
    -0.65
     vacancies
    -0.64
    POSITIVE LOGITS
    uay
    0.98
    zx
    0.88
    udo
    0.86
    ï¸ı
    0.81
    eta
    0.79
    vernment
    0.79
    ppe
    0.71
    andise
    0.71
    orno
    0.70
    edo
    0.70
    Activations Density 0.396%

    No Known Activations