INDEX

Explanations

mentions of recent occurrences, often in relation to reports or statistics

oai_token-act-pair · gpt-3.5-turbo

references to the most recent events or updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

amber

-0.80

rats

-0.77

wright

-0.75

İĭ

-0.74

 teasp

-0.74

avery

-0.73

ingen

-0.72

qqa

-0.72

ocracy

-0.71

hod

-0.70

POSITIVE LOGITS

 incarnation

1.11

 installment

1.05

 iteration

1.00

 edition

0.99

 episode

0.99

 chapter

0.89

 update

0.88

 editions

0.85

 installments

0.85

 version

0.84

Activations Density 0.013%

mentions of recent occurrences, often in relation to reports or statistics

references to the most recent events or updates

No Comments

No Known Activations