INDEX

Explanations

words related to mystical or mysterious concepts

oai_token-act-pair · gpt-3.5-turbo

references to specific titles of movies or artistic works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

coh

-0.98

ccording

-0.95

jri

-0.84

 seiz

-0.84

ĸļ

-0.82

 defic

-0.77

 reflections

-0.76

 nodd

-0.75

 swell

-0.75

 brill

-0.71

POSITIVE LOGITS

[/

0.80

and

0.80

 View

0.78

 Monte

0.73

Ce

0.72

Ana

0.69

andre

0.69

Te

0.67

[[

0.66

 Logged

0.66

Activations Density 0.090%

words related to mystical or mysterious concepts

references to specific titles of movies or artistic works

No Comments

No Known Activations