INDEX

Explanations

sections and references within a document

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

conclusions and summaries

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 numerus

-0.45

 Biôgrafia

-0.43

 ujednoznacz

-0.39

bildēt

-0.36

 camicia

-0.35

 PyTuple

-0.35

 mergeFrom

-0.34

 desayuno

-0.33

 éter

-0.32

titleMargin

-0.32

POSITIVE LOGITS

!*\

0.51

KURZBESCHREIBUNG

0.48

SequentialGroup

0.48



0.47

 समीक्षक

0.47

sbericht

0.45

parsedMessage

0.44

 troubleshooting

0.44

StandardCharsets

0.44

lichung

0.43

Activations Density 0.041%

sections and references within a document

conclusions and summaries

No Comments

No Known Activations