Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 18634
    Prev
    Next
    INDEX
    Explanations

    commands or actions related to detachment or separation

    oai_token-act-pair · gpt-3.5-turbo

    words related to removal or disconnection

    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
    iop
    -0.63
    eson
    -0.62
    eway
    -0.59
     msec
    -0.59
    oppy
    -0.58
     onward
    -0.57
    rano
    -0.56
    riz
    -0.55
     amplification
    -0.55
    tone
    -0.55
    POSITIVE LOGITS
    owship
    1.07
    ociate
    0.79
     altogether
    0.75
    strap
    0.72
    iates
    0.71
    ment
    0.71
     entirely
    0.71
    lesiastical
    0.70
    minded
    0.69
     from
    0.68
    Activations Density 0.186%

    No Known Activations