INDEX

Explanations

references to shells in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 समीक्षाओं

-0.73

awtextra

-0.67

styleType

-0.57

 acceptor

-0.56

Nazionale

-0.56

awakeFromNib

-0.56

argue

-0.56

[]);

-0.55

ihnachten

-0.55

 Stephen

-0.55

POSITIVE LOGITS

 Audio

0.76

Audio

0.72

 shell

0.71

Shell

0.68

 audio

0.65

 Shell

0.65

 AUDIO

0.64

 const

0.63

TestingModule

0.63

AUDIO

0.62

Activations Density 0.079%

references to shells in various contexts

No Comments

No Known Activations