INDEX

Explanations

text related to editing and categorizing content

oai_token-act-pair · gpt-3.5-turbo

references to popular culture and its elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

pload

-0.70

aye

-0.69

essage

-0.60

yang

-0.58

selage

-0.57

ONY

-0.56

nen

-0.56

 TRUMP

-0.55

 Incredible

-0.55

tein

-0.54

POSITIVE LOGITS

ĨĴ

0.84

Magikarp

0.74

 underpin

0.62

 religion

0.61

âĸ¬

0.59

 Latter

0.58

 Buddhism

0.57

 academia

0.57

 sciences

0.57

Â¯Â¯Â¯Â¯

0.54

Activations Density 1.165%

text related to editing and categorizing content

references to popular culture and its elements

No Comments

No Known Activations