INDEX

Explanations

phrases or words indicating various installments or editions of a series, franchise, or program for different types of media

oai_token-act-pair · gpt-3.5-turbo

references to sequential parts of a series or franchise installments

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

yer

-0.83

eric

-0.80

inators

-0.77

verbs

-0.73

gling

-0.73

bara

-0.70

esting

-0.70

ingers

-0.69

estation

-0.68

est

-0.68

POSITIVE LOGITS

 installment

1.02

 installments

0.91

ĸļ

0.78

VII

0.77

 VIII

0.75

 "$:/

0.74

itial

0.73

teenth

0.73

 thereof

0.71

 finale

0.70

Activations Density 0.016%

phrases or words indicating various installments or editions of a series, franchise, or program for different types of media

references to sequential parts of a series or franchise installments

No Comments

No Known Activations