INDEX

Explanations

dates and locations

oai_token-act-pair · gpt-3.5-turbo

phrases related to legal situations and authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

VERTISEMENT

-0.76

 hybrids

-0.76

selves

-0.74

 selves

-0.74

venants

-0.67

 robbery

-0.67

 Splash

-0.66

 robberies

-0.65

 inheritance

-0.62

Origin

-0.62

POSITIVE LOGITS

 himself

1.02

 resign

1.02

 overseeing

1.02

 oversee

0.95

 resigned

0.95

 ministerial

0.92

 personally

0.89

 chair

0.85

 chaired

0.85

 briefed

0.85

Activations Density 1.287%

dates and locations

phrases related to legal situations and authority

No Comments

No Known Activations