INDEX

Explanations

references to specific titles or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 pleaſure

-0.97

 houſe

-0.95

 Monfieur

-0.93

 ſta

-0.92

 Jefus

-0.89

 ſever

-0.89

 raiſ

-0.88

 ſtate

-0.88

 purpoſe

-0.86

 ſte

-0.83

POSITIVE LOGITS

0.48

0.47

 suivantes

0.47

σμα

0.47

miendo

0.46

 Picchu

0.46

explicit

0.46

 induk

0.45

buf

0.45

 Past

0.44

Activations Density 0.068%

references to specific titles or entities

No Comments

No Known Activations