INDEX

Explanations

default-related terminology in data definitions or settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 BorderRadius

-0.77

OGND

-0.75

($__

-0.69

 يتيمه

-0.68

ագրություններ

-0.63

مصادر

-0.61

 setShow

-0.60

ModelSerializer

-0.60

 كومونز

-0.59

utilisons

-0.59

POSITIVE LOGITS

CloseOperation

0.98

情况下

0.75

ing

0.73

值

0.71

값

0.67

 settings

0.59

orescence

0.58

 values

0.58

値

0.57

value

0.56

Activations Density 0.042%

default-related terminology in data definitions or settings

No Comments

No Known Activations