INDEX

Explanations

phrases related to expressing opinions or making decisions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the need for action or change

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

ady

-0.73

izens

-0.65

izen

-0.63

emaker

-0.61

eny

-0.61

afe

-0.59

owe

-0.59

raft

-0.58

ãĤ´ãĥ³

-0.57

ower

-0.57

POSITIVE LOGITS

 yeah

1.06

huh

0.97

 namely

0.92

etc

0.89

sir

0.86

 blah

0.86

 âĢ¦"

0.85

 whereas

0.85

 maybe

0.83

0.82

Activations Density 0.447%

phrases related to expressing opinions or making decisions

phrases indicating the need for action or change

No Comments

No Known Activations