INDEX

Explanations

words related to legal licenses

oai_token-act-pair · gpt-3.5-turbo

terms related to licensing or permits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Garrison

-0.67

 aggregate

-0.66

 override

-0.63

 turnout

-0.60

Pod

-0.60

 theater

-0.60

 overwhelmingly

-0.59

aft

-0.59

 averages

-0.59

pts

-0.59

POSITIVE LOGITS

lic

4.87

lich

1.64

lication

1.47

Lic

1.46

license

1.30

Lic

1.26

lict

1.20

lic

1.13

lo

1.12

lu

1.10

Activations Density 0.021%

words related to legal licenses

terms related to licensing or permits

No Comments

No Known Activations