INDEX

Explanations

phrases related to legal proceedings or court cases

oai_token-act-pair · gpt-3.5-turbo

references to various U.S. District Courts

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

natureconservancy

-0.70

jiang

-0.69

ku

-0.66

 livest

-0.64

 Saban

-0.62

byn

-0.62

glomer

-0.61

lyr

-0.60

hol

-0.59

pee

-0.58

POSITIVE LOGITS

auld

0.97

rooms

0.95

room

0.85

thouse

0.84

esan

0.83

 judge

0.79

wright

0.78

 Judge

0.78

istrate

0.77

Court

0.77

Activations Density 0.029%

phrases related to legal proceedings or court cases

references to various U.S. District Courts

No Comments

No Known Activations