INDEX

Explanations

company names and terms related to business and negotiations

oai_token-act-pair · gpt-3.5-turbo

the word "and" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

hemer

-0.68

espie

-0.66

erie

-0.65

istics

-0.62

>[

-0.60

banks

-0.59

ummer

-0.57

anasia

-0.57

inational

-0.57

cells

-0.57

POSITIVE LOGITS

 other

1.06

 Other

0.97

 others

0.94

Its

0.93

 elsewhere

0.92

 Associates

0.91

 Others

0.89

its

0.85

other

0.83

 adjoining

0.80

Activations Density 0.313%

company names and terms related to business and negotiations

the word "and" in various contexts

No Comments

No Known Activations