INDEX

Explanations

phrases related to probability and likelihood

oai_token-act-pair · gpt-3.5-turbo

phrases indicating probabilities or chances in various contexts

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

æ©Ł

-1.01

çļ

-0.83

æ©

-0.75

NCT

-0.73

idelines

-0.73

UFF

-0.73

é¾į

-0.72

ANC

-0.70

agall

-0.70

âĸ¬

-0.69

POSITIVE LOGITS

 outcome

0.80

 wiser

0.69

 someday

0.69

 apocalypse

0.68

 runaway

0.67

 breakout

0.66

 occurrence

0.66

 doom

0.65

 outcomes

0.65

 accidental

0.64

Activations Density 0.231%

phrases related to probability and likelihood

phrases indicating probabilities or chances in various contexts

No Comments

No Known Activations