INDEX

Explanations

obstacles or challenges

oai_token-act-pair · gpt-3.5-turbo

terms related 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

daq

-0.86

orp

-0.77

orpor

-0.77

orf

-0.75

entric

-0.75

otide

-0.74

zsche

-0.74

ersive

-0.74

esome

-0.74

orks

-0.72

POSITIVE LOGITS

 obstacle

1.18

 obstacles

1.13

 hurdles

1.02

 barriers

0.98

 impede

0.92

 imped

0.90

 hurdle

0.88

 facing

0.86

 obstruction

0.86

 barrier

0.85

Activations Density 0.048%

obstacles or challenges

terms related to challenges or impediments

No Comments

No Known Activations