INDEX

Explanations

items or components in a context that suggests categorization or organization

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

MemoryWarning

-0.76

 Houſe

-0.75

FieldBuilder

-0.75

UnsafeEnabled

-0.74

^(@)

-0.74

 photolibrary

-0.71

noons

-0.71

ſelves

-0.70

Vidite

-0.70

 themſelves

-0.69

POSITIVE LOGITS

it

0.99

 dedans

0.93

 dessus

0.82

 attached

0.80

its

0.69

 thereon

0.68

 مشين

0.68

 therein

0.65

 drauf

0.63

attached

0.61

Activations Density 0.545%

items or components in a context that suggests categorization or organization

No Comments

No Known Activations