INDEX

Explanations

boolean flags and conditions related to statuses or results

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

 виправивши

-0.82

Vidite

-0.75

tonsoft

-0.71

ագրություններ

-0.70

PyExc

-0.70

RegistryLite

-0.69

+#+

-0.69

Efq

-0.66

migrationBuilder

-0.65

LabelTagHelper

-0.65

POSITIVE LOGITS

 flag

0.68

CompoundButton

0.63

flag

0.60

Flag

0.58

 bandera

0.58

flags

0.56

False

0.55

 boolean

0.54

True

0.54

 Flag

0.52

Activations Density 0.228%

boolean flags and conditions related to statuses or results

No Comments

No Known Activations