INDEX

Explanations

references to specific individuals and affiliations in academic or formal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Datuak

-0.91

ARGS

-0.89

 Seton

-0.85

Hozzáférés

-0.84

 Sepp

-0.83

 charité

-0.82

 مشين

-0.80

kaido

-0.76

</em>

-0.75

QMetaType

-0.75

POSITIVE LOGITS

KRA

0.92

 Cram

0.87

GRA

0.86

 Chré

0.81

 Kraw

0.81

 Frazier

0.81

DRA

0.80

 createSprite

0.80

DRA

0.79

Bres

0.78

Activations Density 3.864%

references to specific individuals and affiliations in academic or formal contexts

No Comments

No Known Activations