INDEX

Explanations

words related to usability or playability

oai_token-act-pair · gpt-3.5-turbo

terms related to functionality and usability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

hon

-0.90

set

-0.80

romy

-0.79

olog

-0.79

str

-0.78

yang

-0.78

eve

-0.77

indust

-0.76

ractor

-0.76

otomy

-0.76

POSITIVE LOGITS

 usable

1.03

 playable

1.01

izable

0.84

halla

0.78

isable

0.75

ible

0.75

ABLE

0.74

 habitable

0.73

 readable

0.73

lihood

0.72

Activations Density 0.011%

words related to usability or playability

terms related to functionality and usability

No Comments

No Known Activations