INDEX

Explanations

steps or instructions in a process

oai_token-act-pair · gpt-3.5-turbo

instructional steps or sequences in a process

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

ãĥīãĥ©ãĤ´ãĥ³

-0.76

ãĥ©ãĥ³

-0.75

BIP

-0.74

eatures

-0.68

selage

-0.65

eer

-0.65

 Unic

-0.64

ortunately

-0.64

ãĥĨãĤ£

-0.63

BALL

-0.63

POSITIVE LOGITS

hens

1.05

daughter

1.05

han

0.97

hani

0.95

dad

0.92

hen

0.91

isters

0.90

mother

0.89

brother

0.89

iblings

0.89

Activations Density 0.033%

steps or instructions in a process

instructional steps or sequences in a process

No Comments

No Known Activations