INDEX

Explanations

words related to illness or negative health outcomes

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

Tokens starting with "Ill" or "Pill"

np_acts-logits-general · gemini-2.0-flash

words with "ill" or "pill"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

WEBPACK

-0.90

nalités

-0.76

 Bourgoin

-0.72

tonsoft

-0.71

skjaer

-0.71

waite

-0.70

Eras

-0.69

º

-0.69

emia

-0.69

 LUMP

-0.69

POSITIVE LOGITS

 Sill

0.93

ILL

0.86

ll

0.85

dill

0.85

bill

0.83

mill

0.82

 mills

0.81

Pill

0.81

ills

0.79

ILL

0.79

Activations Density 0.308%

words related to illness or negative health outcomes

Tokens starting with "Ill" or "Pill"

words with "ill" or "pill"

No Comments

No Known Activations