INDEX

Explanations

references to religious texts and figures

oai_token-act-pair · gpt-3.5-turbo

references to religious texts and figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bledon

-0.81

leneck

-0.80

pless

-0.78

rared

-0.77

llular

-0.77

ptive

-0.74

ovo

-0.74

 srfAttach

-0.73

osponsors

-0.72

jri

-0.72

POSITIVE LOGITS

 Interpret

1.11

 narrated

0.94

 verse

0.94

 narration

0.90

 narr

0.89

 verses

0.87

 manuscripts

0.87

 manuscript

0.87

 texts

0.86

 Romans

0.86

Activations Density 0.172%

references to religious texts and figures

references to religious texts and figures

No Comments

No Known Activations