INDEX

Explanations

phrases that indicate a continuing explanation or reference to previous points in a text

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



-0.69

pédie

-0.61

NUMX

-0.60

Ngb

-0.60

latego

-0.57

⁨

-0.57

rvore

-0.57

itaires

-0.56

 prefeito

-0.56

Jawaban

-0.56

POSITIVE LOGITS

 follow

1.70

 follows

1.58

follow

1.52

 FOLLOW

1.42

 Follow

1.36

 Follows

1.33

Follow

1.33

follows

1.32

 followed

1.11

FOLLOW

1.11

Activations Density 0.129%

phrases that indicate a continuing explanation or reference to previous points in a text

No Comments

No Known Activations