© 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. 18563
    Prev
    Next
    INDEX
    Explanations

    information related to organizing events or activities, especially in a formal or coordinated manner

    oai_token-act-pair · gpt-3.5-turbo

    structures and contributions related to event organization or administration

    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
     Penny
    -0.53
     playbook
    -0.52
     Deadpool
    -0.51
     Vince
    -0.50
     staffers
    -0.50
     Coco
    -0.50
     hindsight
    -0.49
     Dominic
    -0.48
    Ultimately
    -0.48
     POLITICO
    -0.48
    POSITIVE LOGITS
     respectively
    0.70
     hapl
    0.68
     surname
    0.60
     Variant
    0.58
    cerning
    0.57
    osate
    0.57
     âĵĺ
    0.56
    è¦ļéĨĴ
    0.55
    uese
    0.55
     partition
    0.55
    Activations Density 2.876%

    No Known Activations