INDEX

Explanations

references to objects or concepts considered sacred

oai_token-act-pair · gpt-3.5-turbo

terms and phrases that denote something considered sacred or holy

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

annis

-0.85

 Hust

-0.75

ocre

-0.75

mington

-0.72

OPA

-0.72

ello

-0.71

schild

-0.71

ocate

-0.70

err

-0.69

SN

-0.68

POSITIVE LOGITS

 rites

0.99

 scripture

0.95

ness

0.93

 cows

0.92

 maiden

0.85

 scriptures

0.85

 sacred

0.85

 oath

0.85

 sanct

0.84

 rite

0.83

Activations Density 0.027%

references to objects or concepts considered sacred

terms and phrases that denote something considered sacred or holy

No Comments

No Known Activations