INDEX

Explanations

Legal terms related to a court case, such as plaintiffs and allegations

oai_token-act-pair · gpt-3.5-turbo

references to plaintiffs in legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

[|

-0.78

adena

-0.74

inventoryQuantity

-0.72

OVA

-0.71

kefeller

-0.70

apes

-0.69

apo

-0.69

lasses

-0.69

ollo

-0.68

ahime

-0.68

POSITIVE LOGITS

 plaintiffs

0.97

iffs

0.86

 plaintiff

0.82

 suing

0.78

 defendants

0.74

 Plaint

0.74

 attorneys

0.71

 claimant

0.71

Lov

0.68

 alleges

0.68

Activations Density 0.032%

Legal terms related to a court case, such as plaintiffs and allegations

references to plaintiffs in legal contexts

No Comments

No Known Activations