INDEX

Explanations

phrases indicating inevitability or a certain outcome

oai_token-act-pair · gpt-3.5-turbo

the phrase "a matter of time."

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

pps

-0.78

uras

-0.72

ovi

-0.71

notations

-0.69

Tur

-0.67

querade

-0.66

cci

-0.66

 Guides

-0.65

luaj

-0.64

ako

-0.64

POSITIVE LOGITS

 sorts

0.72

 luck

0.71

 course

0.69

 simmer

0.68

 jurisdiction

0.68

 justice

0.66

 JUSTICE

0.65

 whether

0.65

 milliseconds

0.64

milo

0.64

Activations Density 0.047%

phrases indicating inevitability or a certain outcome

the phrase "a matter of time."

No Comments

No Known Activations