INDEX

Explanations

legal terminology or references to courts and their decisions

oai_token-act-pair · gpt-3.5-turbo

references to the court system and judicial decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 livest

-0.72

jiang

-0.71

 plent

-0.69

 Motorsport

-0.68

 Nato

-0.68

ktop

-0.67

Tao

-0.66

 Marketable

-0.64

 Pyro

-0.64

ana

-0.63

POSITIVE LOGITS

rooms

1.06

room

0.98

 justices

0.91

wright

0.87

Court

0.81

iffs

0.80

court

0.80

yer

0.76

NEY

0.74

yers

0.74

Activations Density 0.026%

legal terminology or references to courts and their decisions

references to the court system and judicial decisions

No Comments

No Known Activations