INDEX

Explanations

instances of acknowledgment or admission of wrongdoing

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

ValueStyle

-0.73

">//

-0.73

LikeLike

-0.71

ClientSize

-0.68

THON

-0.65

loyees

-0.65

idigung

-0.65

iecie

-0.64

CGContext

-0.64

fjspx

-0.64

POSITIVE LOGITS

 Admit

1.52

 admit

1.47

 admitted

1.37

 admits

1.36

 Admissions

1.35

 admitting

1.32

 admissions

1.28

Admissions

1.21

 confesses

1.18

 Admission

1.17

Activations Density 0.124%

instances of acknowledgment or admission of wrongdoing

No Comments

No Known Activations