INDEX

Explanations

references to specific TV shows and their details

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 consultato

-0.98

UnknownFieldSet

-0.97

ValueStyle

-0.95

 propOrder

-0.88

دانشنامهٔ

-0.85

MigrationBuilder

-0.84

 transférez

-0.84

sizeCache

-0.82

__*/

-0.81

GEBURTSDATUM

-0.81

POSITIVE LOGITS

Matters

0.47

 tuong

0.46

issippi

0.46

ufe

0.46

 merve

0.46

 Matters

0.46

 segn

0.46

enoch

0.45

 maxn

0.44

 paſſ

0.44

Activations Density 0.107%

references to specific TV shows and their details

No Comments

No Known Activations