INDEX

Explanations

terms related to future events or possibilities

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "horizon"

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

UGC

-0.90

Downloadha

-0.80

ublic

-0.76

ERC

-0.74

aud

-0.73

NetMessage

-0.71

piracy

-0.71

oly

-0.70

uana

-0.69

ECA

-0.68

POSITIVE LOGITS

 horizon

1.24

izons

1.19

wip

0.79

 lobe

0.79

ward

0.74

naire

0.72

 hawk

0.72

illary

0.70

 skyline

0.70

Activations Density 0.016%

terms related to future events or possibilities

mentions of the word "horizon"

No Comments

No Known Activations