INDEX

Explanations

mentions of legal proceedings, specifically related to pleas and bargains

oai_token-act-pair · gpt-3.5-turbo

references to legal plea agreements or bargains

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

ONES

-0.73

orians

-0.72

idays

-0.71

aughters

-0.71

lav

-0.68

-0.67

ians

-0.67

icky

-0.65

orrect

-0.65

 Kers

-0.65

POSITIVE LOGITS

 plea

1.08

 bargain

1.04

 plead

0.99

 barg

0.96

 pled

0.93

 pleading

0.87

 bargaining

0.79

 Ramsey

0.79

 sentencing

0.78

 parole

0.77

Activations Density 0.011%

mentions of legal proceedings, specifically related to pleas and bargains

references to legal plea agreements or bargains

No Comments

No Known Activations