INDEX

Explanations

acronyms or specific terms related to a subject matter

oai_token-act-pair · gpt-3.5-turbo

references to a specific organization or publication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 congr

-0.77

served

-0.77

phia

-0.75

 counselor

-0.74

yrinth

-0.72

anwhile

-0.70

 counselors

-0.69

rule

-0.68

ĺħ

-0.68

esian

-0.67

POSITIVE LOGITS

terson

0.99

ting

0.99

 Beir

0.90

WT

0.85

oxin

0.83

ted

0.82

hered

0.81

ICAN

0.80

ypes

0.79

izont

0.78

Activations Density 0.017%

acronyms or specific terms related to a subject matter

references to a specific organization or publication

No Comments

No Known Activations