INDEX

Explanations

references to speech or statements made in the text

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

"say" or variants

np_acts-logits-general · gemini-2.0-flash

saying something or being said

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

']")

-0.67

 Malte

-0.66

`]

-0.66

ㅋㅋ

-0.64

 Staub

-0.63

 <<<<<<<<<<<<<<

-0.61

TagHelpers

-0.61

Dez

-0.60

Архівовано

-0.59

URB

-0.59

POSITIVE LOGITS

Say

1.19

SAY

1.14

SAY

1.09

Say

1.07

say

1.04

say

1.00

 Says

0.96

 says

0.93

 goodbye

0.89

 SAYS

0.88

Activations Density 0.098%

references to speech or statements made in the text

"say" or variants

saying something or being said

No Comments

No Known Activations