INDEX

Explanations

specific punctuation and formatting characters, likely in programming or markup context

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

observable, computed, equal, assert

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 queſta

-0.98

parsedMessage

-0.96

 betweenstory

-0.87

 صوتيه

-0.83

uxxxx

-0.81

postIndex

-0.80

новништво

-0.77

 pleaſure

-0.76

 ſche

-0.75

 beginnetje

-0.75

POSITIVE LOGITS

be

0.57

0.54

not

0.50

 have

0.45

0.42

0.41

0.40

0.39

 wildly

0.38

Activations Density 0.001%

specific punctuation and formatting characters, likely in programming or markup context

observable, computed, equal, assert

No Comments

No Known Activations