INDEX

Explanations

words related to obstacles

oai_token-act-pair · gpt-3.5-turbo

references to challenges or impediments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orp

-0.87

akening

-0.74

entric

-0.73

otide

-0.72

ropolitan

-0.72

zsche

-0.72

daq

-0.71

orf

-0.70

ovy

-0.70

orks

-0.69

POSITIVE LOGITS

 obstacle

1.10

 hurdles

1.09

 obstacles

1.07

 barriers

0.97

 hurdle

0.91

 imped

0.90

 facing

0.85

 impede

0.79

 insur

0.78

 preventing

0.78

Activations Density 0.040%

words related to obstacles

references to challenges or impediments

No Comments

No Known Activations