INDEX

Explanations

phrases related to legal actions or claims

oai_token-act-pair · gpt-3.5-turbo

legal terminology related to lawsuits and allegations

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

OVA

-0.78

cffffcc

-0.73

talk

-0.72

 Assass

-0.72

elight

-0.72

Recipe

-0.71

 "$:/

-0.71

mable

-0.70

obyl

-0.70

Ranked

-0.69

POSITIVE LOGITS

 alleging

0.97

 alleges

0.94

 suing

0.93

sue

0.89

 allege

0.88

 attorneys

0.87

 filed

0.86

 attorney

0.82

 sued

0.81

iffs

0.79

Activations Density 0.098%

phrases related to legal actions or claims

legal terminology related to lawsuits and allegations

No Comments

No Known Activations