INDEX

Explanations

evidence related to legal cases

oai_token-act-pair · gpt-3.5-turbo

references to various forms of evidence in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

•Evidence

No Comments

Negative Logits

ategory

-0.95

ttle

-0.72

Hop

-0.71

TOR

-0.70

awar

-0.69

orks

-0.68

frey

-0.68

ernel

-0.66

orus

-0.66

onen

-0.66

POSITIVE LOGITS

 tampering

1.03

 evidence

1.00

evidence

1.00

 Evidence

0.83

edly

0.81

 evid

0.79

proof

0.79

Evidence

0.78

 testifying

0.77

 gathered

0.77

Activations Density 0.027%

evidence related to legal cases

references to various forms of evidence in a context

No Comments

No Known Activations