INDEX

Explanations

phrases related to significant concerns or factors

oai_token-act-pair · gpt-3.5-turbo

phrases indicating significant concerns or factors related to various issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

hops

-0.78

deen

-0.71

flix

-0.68

oval

-0.67

 raids

-0.67

earances

-0.67

etsk

-0.66

ieval

-0.66

dos

-0.65

 funer

-0.65

POSITIVE LOGITS

 factor

1.52

 reason

1.37

 motiv

1.27

 motivating

1.27

factor

1.27

 indicator

1.22

 criterion

1.14

 hurdle

1.14

 determining

1.13

 factors

1.13

Activations Density 0.227%

phrases related to significant concerns or factors

phrases indicating significant concerns or factors related to various issues

No Comments

No Known Activations