INDEX

Explanations

mentions of alleged or related allegations

oai_token-act-pair · gpt-3.5-turbo

terms related to accusations or allegations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

OVA

-0.77

live

-0.75

bern

-0.72

ajo

-0.71

vet

-0.71

haar

-0.71

eyes

-0.70

patch

-0.70

ben

-0.70

ARCH

-0.70

POSITIVE LOGITS

 allegations

0.90

 accuser

0.82

 accusations

0.81

 disclosures

0.76

 alleged

0.76

 abuses

0.75

 misrepresent

0.73

 abuser

0.73

 accused

0.73

 alleges

0.72

Activations Density 0.015%

mentions of alleged or related allegations

terms related to accusations or allegations

No Comments

No Known Activations