INDEX

Explanations

names of physical places or organizations

oai_token-act-pair · gpt-3.5-turbo

words related to proof or evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

geist

-0.81

lasses

-0.75

mare

-0.70

 count

-0.67

 Eclipse

-0.66

 Rite

-0.66

Reloaded

-0.65

Pie

-0.65

DEN

-0.62

mite

-0.61

POSITIVE LOGITS

idence

1.34

idential

1.20

idently

1.16

isions

1.15

idences

1.12

iders

1.02

ident

0.98

esses

0.96

irus

0.95

identally

0.93

Activations Density 0.014%

names of physical places or organizations

words related to proof or evidence

No Comments

No Known Activations