INDEX

Explanations

punctuation marks and formatting cues in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

-0.64

-0.58

-0.56

sk

-0.54

tra

-0.52

mor

-0.51

Sch

-0.51

ST

-0.50

POSITIVE LOGITS

 pleaſure

1.31

GEBURTSDATUM

1.19

 purpoſe

1.14

 houſe

1.14

 myſelf

1.13

ſelf

1.12

 anſ

1.10

 raiſ

1.10

 diſt

1.10

UnsafeEnabled

1.08

Activations Density 0.301%

punctuation marks and formatting cues in the text

No Comments

No Known Activations