INDEX

Explanations

instances where something is no longer possible or allowed

oai_token-act-pair · gpt-3.5-turbo

phrases expressing negation or denial

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

RAFT

-0.66

romeda

-0.65

romy

-0.58

ATIVE

-0.57

realDonaldTrump

-0.56

endar

-0.55

ropolitan

-0.55

rex

-0.54

heid

-0.53

thora

-0.53

POSITIVE LOGITS

xious

1.35

 longer

1.30

 matter

1.02

ct

1.00

icably

0.97

xus

0.93

 doubt

0.89

obs

0.88

otrop

0.83

vell

0.83

Activations Density 0.069%

instances where something is no longer possible or allowed

phrases expressing negation or denial

No Comments

No Known Activations