INDEX

Explanations

words related to being compelled or required to do something against one's will

oai_token-act-pair · gpt-3.5-turbo

instances of the word "forced."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ership

-0.76

ergy

-0.74

vironment

-0.70

 Cannabis

-0.70

gdala

-0.66

issance

-0.66

 Budd

-0.65

itect

-0.64

amac

-0.64

LAN

-0.64

POSITIVE LOGITS

ierrez

0.85

 overtime

0.79

 forced

0.75

 laborers

0.74

 conversions

0.72

untarily

0.71

 labou

0.69

 displacement

0.69

 diseng

0.69

ãĥ©ãĥ³

0.68

Activations Density 0.018%

words related to being compelled or required to do something against one's will

instances of the word "forced."

No Comments

No Known Activations