INDEX

Explanations

words related to transformations, changes, and transitions

oai_token-act-pair · gpt-3.5-turbo

entities or concepts related to identity transformation or status changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 balances

-0.63

arton

-0.62

 bene

-0.61

 similarity

-0.60

 caveats

-0.60

 unpublished

-0.59

)\

-0.58

ups

-0.58

ibrary

-0.57

 misconception

-0.57

POSITIVE LOGITS

 fodder

0.81

 scapego

0.78

livion

0.77

sonian

0.75

 anew

0.75

fledged

0.73

 overnight

0.72

Normal

0.71

 unemploy

0.70

resistant

0.67

Activations Density 0.361%

words related to transformations, changes, and transitions

entities or concepts related to identity transformation or status changes

No Comments

No Known Activations