INDEX

Explanations

words related to detection, particularly verbs indicating the action of discovering or identifying something

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of detection and identifying

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

mort

-0.94

emate

-0.76

nesia

-0.73

egal

-0.72

erer

-0.71

ember

-0.70

ovie

-0.70

adra

-0.68

itent

-0.67

ammy

-0.67

POSITIVE LOGITS

 flaws

0.85

ively

0.81

 faults

0.77

 detection

0.72

 Detection

0.72

 detect

0.70

ibly

0.69

ible

0.68

 leakage

0.68

 weaknesses

0.67

Activations Density 0.042%

words related to detection, particularly verbs indicating the action of discovering or identifying something

terms related to the concept of detection and identifying

No Comments

No Known Activations