© 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. 6-RES-JB
    11. 2619
    Prev
    Next
    INDEX
    Explanations

    objects or products associated with specific materials or functionalities

    oai_token-act-pair · gpt-3.5-turbo

    products or items related to hobbies or leisure activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bidden
    -0.77
    utenberg
    -0.75
    ©¶æ¥µ
    -0.70
    ģ«
    -0.70
    putable
    -0.69
    udden
    -0.68
    imately
    -0.66
    76561
    -0.65
     Contribut
    -0.65
    âķIJâķIJ
    -0.64
    POSITIVE LOGITS
    caster
    0.77
     puck
    0.73
     racer
    0.72
     cleaner
    0.70
     robot
    0.70
     macro
    0.69
     sculpture
    0.68
     blaster
    0.67
    apter
    0.67
     launcher
    0.65
    Activations Density 0.467%

    No Known Activations