INDEX

Explanations

programming-related terms and commands

oai_token-act-pair · gpt-3.5-turbo

technical terms related to coding and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

eatures

-0.98

etheless

-0.89

 destro

-0.82

icum

-0.80

ighting

-0.79

 carbohyd

-0.79

atile

-0.76

swick

-0.75

 exha

-0.75

ilitary

-0.74

POSITIVE LOGITS

lihood

1.36

able

1.16

ABLE

1.00

ables

0.99

ments

0.98

ings

0.91

ability

0.81

vier

0.80

MENTS

0.78

ment

0.76

Activations Density 0.197%

programming-related terms and commands

technical terms related to coding and programming

No Comments

No Known Activations