INDEX

Explanations

obstacles or hindrances in various contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to barriers or challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ulet

-0.83

elt

-0.83

akening

-0.79

orpor

-0.76

erd

-0.73

urgy

-0.72

akin

-0.71

overe

-0.71

erk

-0.71

daq

-0.70

POSITIVE LOGITS

 obstacle

1.23

 obstacles

1.10

 imped

0.98

 obstruction

0.91

 impede

0.86

 hurdles

0.85

 barriers

0.80

 obstruct

0.80

 hinder

0.77

 hurdle

0.77

Activations Density 0.017%

obstacles or hindrances in various contexts

terms related to barriers or challenges

No Comments

No Known Activations