INDEX

Explanations

phrases related to underground structures like burrows

oai_token-act-pair · gpt-3.5-turbo

mentions of "bur" related content, particularly burrows

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

é¾įå

-0.85

)=(

-0.82

FTWARE

-0.77

å§«

-0.74

 Nanto

-0.73

éĹĺ

-0.72

externalActionCode

-0.71

Management

-0.71

[&

-0.69

aunder

-0.69

POSITIVE LOGITS

rito

1.22

rowing

1.14

rows

1.12

bur

1.10

pees

1.09

rit

1.06

pee

1.05

row

1.02

riter

0.99

gey

0.98

Activations Density 0.010%

phrases related to underground structures like burrows

mentions of "bur" related content, particularly burrows

No Comments

No Known Activations