INDEX

Explanations

adjectives describing something intriguing, challenging, or remarkable

oai_token-act-pair · gpt-3.5-turbo

adjectives that describe complexity or challenge

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

events

-0.84

apons

-0.82

assies

-0.80

doms

-0.79

apses

-0.79

votes

-0.78

thood

-0.77

 stamps

-0.76

ravings

-0.74

ults

-0.72

POSITIVE LOGITS

 reminder

0.99

 contributor

0.91

 sleeper

0.90

 contender

0.90

 proposition

0.89

 example

0.89

 boon

0.88

 asset

0.88

 antidote

0.87

 inhibitor

0.85

Activations Density 0.321%

adjectives describing something intriguing, challenging, or remarkable

adjectives that describe complexity or challenge

No Comments

No Known Activations