INDEX

Explanations

function calls and logging statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

__':

-0.82

.~(\

-0.77

?».

-0.71

Efq

-0.70

(«

-0.69

')):

-0.67



-0.67

<",

-0.66

 mxArray

-0.65

 (‘

-0.64

POSITIVE LOGITS

Inside

0.68

 Inside

0.68

 inside

0.64

inside

0.64

!!!!!!!!

0.60

!!!!!!

0.60

!!!!

0.60

 here

0.57

aaaaaaaa

0.57

llllllll

0.57

Activations Density 0.095%

function calls and logging statements in code

No Comments

No Known Activations

function calls and logging statements in code

No Comments

No Known Activations