INDEX

Explanations

specific strings like 'ON' or 'in' within a text

oai_token-act-pair · gpt-3.5-turbo

specific prepositions and their variations

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

 Revelations

-0.74

 Quadro

-0.68

ATTLE

-0.66

 laughter

-0.64

ĳå£«

-0.63

enance

-0.63

 Penguins

-0.62

 ---------

-0.59

 exits

-0.58

 Buildings

-0.58

POSITIVE LOGITS

jin

1.04

ichi

0.98

ghai

0.92

kered

0.92

hiro

0.91

ji

0.91

ju

0.88

hao

0.88

ori

0.88

nan

0.87

Activations Density 0.095%

specific strings like 'ON' or 'in' within a text

specific prepositions and their variations

No Comments

No Known Activations