INDEX

Explanations

words related to reasons or intentions behind actions

oai_token-act-pair · gpt-3.5-turbo

terms related to motives or reasons behind actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

thumbnails

-0.92

semble

-0.84

ropolis

-0.80

ummer

-0.73

mark

-0.72

hap

-0.70

enegger

-0.70

opy

-0.69

owship

-0.69

kson

-0.68

POSITIVE LOGITS

 motives

1.07

 justifying

1.02

 motive

0.99

 behind

0.96

 motivations

0.95

 rationale

0.91

why

0.84

 motivation

0.82

WHY

0.78

 reasoning

0.77

Activations Density 0.040%

words related to reasons or intentions behind actions

terms related to motives or reasons behind actions

No Comments

No Known Activations