INDEX

Explanations

terms related to legal proceedings and incarceration, specifically focusing on the concept of "parole."

oai_token-act-pair · gpt-3.5-turbo

terms related to parole and corrections

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

sonian

-0.90

 Grimm

-0.77

iance

-0.68

advertisement

-0.68

awei

-0.67

 Ember

-0.64

amped

-0.63

igr

-0.63

ies

-0.61

acters

-0.61

POSITIVE LOGITS

 parole

1.19

 probation

0.84

reon

0.82

 Ribbon

0.81

 revocation

0.81

 versa

0.78

 eligibility

0.73

 commissions

0.72

 clearance

0.72

ctors

0.69

Activations Density 0.013%

terms related to legal proceedings and incarceration, specifically focusing on the concept of "parole."

terms related to parole and corrections

No Comments

No Known Activations