INDEX

Explanations

lines of code that indicate output or error reporting functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

principalTable

-0.77

enumii

-0.74

Personendaten

-0.73

aarrggbb

-0.73

AntiForgeryToken

-0.70

AddTagHelper

-0.69

mergeFrom

-0.69

ⓧ

-0.69

indest

-0.66

CompleteListener

-0.66

POSITIVE LOGITS

fflush

0.92

exit

0.60

 trajets

0.58

 getchar

0.57

 exit

0.56

"))

0.52

 prints

0.52

sys

0.50

prints

0.50

 Cire

0.49

Activations Density 0.051%

lines of code that indicate output or error reporting functionality

No Comments

No Known Activations