INDEX

Explanations

references to sets of items or concepts within theoretical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ftance

-0.92

couvrez

-0.86

voorbeeld

-0.85

ftances

-0.83

RESP

-0.80

SerializedSize

-0.78

OfBirth

-0.76

 carab

-0.76

сылкі

-0.76

føring

-0.74

POSITIVE LOGITS

SET

1.48

set

1.48

set

1.43

Set

1.43

Set

1.42

SET

1.30

 sets

1.29

 Sets

1.26

sets

1.18

 Seton

1.18

Activations Density 0.114%

references to sets of items or concepts within theoretical contexts

No Comments

No Known Activations