INDEX

Explanations

evidence or arguments supporting or refuting different ideas or claims

oai_token-act-pair · gpt-3.5-turbo

phrases that support or refute popular perceptions or notions

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

 actionGroup

-0.79

ufact

-0.71

 Browse

-0.71

 unfocusedRange

-0.70

 GOODMAN

-0.70

Events

-0.69

 overcame

-0.68

phabet

-0.67

Â·Â·

-0.66

meet

-0.65

POSITIVE LOGITS

 assertion

1.69

 assertions

1.66

 claim

1.65

 notion

1.61

 hypothesis

1.60

 claims

1.59

 hypotheses

1.55

 assumption

1.53

 allegation

1.47

 theories

1.47

Activations Density 0.444%

evidence or arguments supporting or refuting different ideas or claims

phrases that support or refute popular perceptions or notions

No Comments

No Known Activations