INDEX

Explanations

terms related to a specific religious figure or text

oai_token-act-pair · gpt-3.5-turbo

references to religious leaders and texts

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

mson

-0.84

 Hurricanes

-0.83

auga

-0.79

xit

-0.77

umbnail

-0.76

swick

-0.73

orph

-0.71

oples

-0.71

 Gators

-0.71

urable

-0.68

POSITIVE LOGITS

 rabb

1.00

 rabbi

0.97

×©

0.92

×ľ

0.92

anyahu

0.91

 Rabbi

0.91

 Netanyahu

0.86

 Torah

0.86

×

0.85

×ķ

0.85

Activations Density 0.047%

terms related to a specific religious figure or text

references to religious leaders and texts

No Comments

No Known Activations