INDEX

Explanations

references to specific locations or items related to food

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Dyer

-0.55

ss

-0.54

 amico

-0.51

AT

-0.51

inflater

-0.50

ec

-0.50

-0.49

StructEnd

-0.48

ert

-0.48

test

-0.48

POSITIVE LOGITS

pit

1.05

 punch

0.95

Pit

0.93

 Johnny

0.93

Pit

0.92

Johnny

0.91

 صوتيه

0.91

 bowl

0.87

pit

0.86

PIT

0.86

Activations Density 0.089%

references to specific locations or items related to food

No Comments

No Known Activations