INDEX

Explanations

the word "injunction" or related legal terms

oai_token-act-pair · gpt-3.5-turbo

terms related to legal injunctions and restraining orders

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

olls

-0.79

rics

-0.75

apest

-0.72

UX

-0.70

hematic

-0.69

ħĭ

-0.68

 Univers

-0.67

morph

-0.67

onut

-0.66

 Loaded

-0.66

POSITIVE LOGITS

 injunction

1.11

 restraining

1.03

 subpoen

0.87

 against

0.86

 decree

0.85

 prohibiting

0.84

 proceedings

0.83

ishment

0.81

 forb

0.79

 warr

0.79

Activations Density 0.012%

the word "injunction" or related legal terms

terms related to legal injunctions and restraining orders

No Comments

No Known Activations