INDEX

Explanations

occurrences of apostrophes indicating contractions or possessives

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

list item separators

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

Negative Logits

CloseOperation

-0.57

httphttps

-0.49

 noDo

-0.48

힣

-0.48

 GenerationType

-0.47

++)

-0.46

ochim

-0.46

endsection

-0.45

 ProtoMessage

-0.45

tagHelperRunner

-0.44

POSITIVE LOGITS

ódnica

0.44

mær

0.40

PYX

0.40

Xna

0.37

the

0.36

 precisione

0.35

#+#

0.35

 Photocase

0.35

beginPath

0.35

UnusedPrivate

0.35

Activations Density 0.012%

occurrences of apostrophes indicating contractions or possessives

list item separators

No Known Activations