INDEX

Explanations

admissions and confessions related to involvement in wrongdoing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 snippetHide

-0.69

ruptedException

-0.65

Hauptartikel

-0.64

esgue

-0.63

ropriate

-0.62

łaj

-0.62

Dra

-0.62

hakti

-0.61

:+:

-0.60

 Barrios

-0.60

POSITIVE LOGITS

 admit

2.06

 admitting

2.00

 admitted

2.00

 admits

1.96

 Admit

1.96

 confessed

1.79

 confess

1.75

 confesses

1.72

 confession

1.56

 admission

1.55

Activations Density 0.113%

admissions and confessions related to involvement in wrongdoing

No Comments

No Known Activations