INDEX

Explanations

elements related to visual representations in academic figures or panels

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

Tokens appearing before enumerated lists/sections

np_acts-logits-general · gemini-2.0-flash

lists and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 initComponents

-0.95

 ſeveral

-0.93

 itſelf

-0.90

 myſelf

-0.85

 uſed

-0.84

ſelves

-0.82

 themſelves

-0.80

 Diſ

-0.79

 ſhe

-0.78

\{\\

-0.78

POSITIVE LOGITS

 illetve

0.79

 voire

0.64

 alike

0.63

respectively

0.62

 perhaps

0.57

 posteriores

0.56

possibly

0.55

 maybe

0.55

 possibly

0.55

Activations Density 0.834%

elements related to visual representations in academic figures or panels

Tokens appearing before enumerated lists/sections

lists and references

No Comments

No Known Activations