INDEX

Explanations

instances of accusations or criticisms related to actions or statements made by individuals, particularly in legal or political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 another

-0.56

 then

-0.56

then

-0.46

こちらも

-0.43

 there

-0.43

 other

-0.43

him

-0.42

 past

-0.42

 next

-0.41

ibid

-0.40

POSITIVE LOGITS

rungsseite

1.02

SequentialGroup

0.84

 Signalez

0.83

tvguidetime

0.83

tagHelperRunner

0.83

 ostavi

0.82

 Specifically

0.80

 createSlice

0.80

enterOuterAlt

0.79

kháu

0.79

Activations Density 0.121%

instances of accusations or criticisms related to actions or statements made by individuals, particularly in legal or political contexts

No Comments

No Known Activations