© 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. 11-RES-JB
    11. 18836
    Prev
    Next
    INDEX
    Explanations

    phrases related to passing through physical obstacles or challenges

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to navigation or movement through various spaces or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CTV
    -0.75
    acea
    -0.70
    Instance
    -0.68
    Percent
    -0.67
    Owner
    -0.67
    POSE
    -0.66
    NAME
    -0.66
    Created
    -0.65
    Table
    -0.65
    seless
    -0.65
    POSITIVE LOGITS
     maze
    1.32
     hoops
    1.31
     motions
    1.27
     gates
    1.26
     hurdles
    1.17
     labyrinth
    1.15
     haze
    1.08
     halls
    1.08
     barriers
    1.08
     obstacles
    1.07
    Activations Density 0.194%

    No Known Activations