INDEX

Explanations

references to specifications or related scientific terminology

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

omla

-0.80

fromCharCode

-0.69

 Anja

-0.62

lloworld

-0.60

mación

-0.59

chuga

-0.59

HandleFunc

-0.57

ISF

-0.56

ђа

-0.56

 Guill

-0.56

POSITIVE LOGITS

 spec

1.15

 SPEC

1.10

 Spec

1.09

SPEC

1.06

 Speck

0.97

Spec

0.95

spec

0.92

rspec

0.90

 Specs

0.89

 espec

0.86

Activations Density 0.142%

references to specifications or related scientific terminology

No Comments

No Known Activations