INDEX

Explanations

numerical values annotated with special symbols, and programming syntax

oai_token-act-pair · gpt-3.5-turbo

terms related to voting and rankings

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

UL

-0.92

Alc

-0.83

AG

-0.83

 Albania

-0.82

ulas

-0.81

 Alonso

-0.81

Âº

-0.80

 Belg

-0.79

Alabama

-0.78

 Xavier

-0.77

POSITIVE LOGITS

read

1.00

reader

0.93

 skim

0.93

play

0.87

 reader

0.86

 PLAY

0.86

 Myers

0.84

 Reader

0.84

 lear

0.82

TL

0.79

Activations Density 0.457%

numerical values annotated with special symbols, and programming syntax

terms related to voting and rankings

No Comments

No Known Activations