INDEX

Explanations

phrases related to specific dates or events

oai_token-act-pair · gpt-3.5-turbo

specific punctuation marks and formatting symbols

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

 Ludwig

-0.88

Todd

-0.86

Bor

-0.83

 Kling

-0.79

Tor

-0.79

 Todd

-0.78

Gan

-0.78

 Tire

-0.77

-0.76

Å

-0.76

POSITIVE LOGITS

->

0.89

apesh

0.83

->

0.82

fn

0.79

 Sorceress

0.78

/"

0.77

igible

0.76

exc

0.76

ql

0.75

 McGr

0.75

Activations Density 0.457%

phrases related to specific dates or events

specific punctuation marks and formatting symbols

No Comments

No Known Activations