INDEX

Explanations

instances of the word "widely," indicating a focus on commonality or widespread acceptance

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PerformLayout

-0.78

na

-0.68

แน

-0.64

ogeneity

-0.64

 Spill

-0.61

peutic

-0.60

chede

-0.60

axel

-0.60

-0.59

POSITIVE LOGITS

 themſelves

0.95

Efq

0.86

ſelves

0.85

 uſe

0.82

 pleaſure

0.82

 myſelf

0.82

GHIJKLM

0.82

ſelf

0.79

 fhew

0.78

sgn

0.77

Activations Density 0.006%

instances of the word "widely," indicating a focus on commonality or widespread acceptance

No Comments

No Known Activations