INDEX

Explanations

statements expressing beliefs

oai_token-act-pair · gpt-3.5-turbo

expressions of belief or conviction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

conservancy

-0.82

practice

-0.73

pmwiki

-0.71

tnc

-0.68

ammy

-0.65

yna

-0.65

details

-0.62

umber

-0.62

skill

-0.62

agher

-0.62

POSITIVE LOGITS

 believe

0.91

 believes

0.78

BEL

0.76

ieve

0.71

itial

0.71

ibles

0.69

 believing

0.68

rill

0.68

oglu

0.67

 convinced

0.67

Activations Density 0.031%

statements expressing beliefs

expressions of belief or conviction

No Comments

No Known Activations