INDEX

Explanations

terms related to health conditions and treatments

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tvguidetime

-0.66

 dezelve

-0.65

ſcher

-0.64

 Waſſer

-0.61

 ſind

-0.61

ſchen

-0.60

iſen

-0.59

 ſein

-0.58

majánló

-0.58

OLEAN

-0.57

POSITIVE LOGITS

[toxicity=0]

0.47

0.43

 intptr

0.40

väg

0.36

xmlns

0.36

">(</

0.35

ibouti

0.34

ią

0.33

LikeLiked

0.33

">—

0.33

Activations Density 0.680%

terms related to health conditions and treatments

No Comments

No Known Activations