INDEX

Explanations

functions and logging statements in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

CppMethod

-0.74



-0.73

 ComVisible

-0.73

 ويكيميديا

-0.71

 invokingState

-0.69

 newBuilder

-0.66

UrlResolution

-0.65

InputTagHelper

-0.64

ItemBackground

-0.64

AsUp

-0.63

POSITIVE LOGITS

The

0.65

 This

0.61

enderror

0.60

IG

0.56

The

0.56

ther

0.56

0.54

To

0.54

 really

0.54

0.53

Activations Density 0.049%

functions and logging statements in code snippets

No Comments

No Known Activations