INDEX

Explanations

phrases related to giving orders or instructions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "ordered."

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

pmwiki

-0.81

Ott

-0.79

doi

-0.77

Wallet

-0.76

tur

-0.75

td

-0.74

bil

-0.74

Footnote

-0.72

tex

-0.71

Marginal

-0.71

POSITIVE LOGITS

 ordered

1.12

 ordering

1.10

avorite

0.94

 orders

0.90

etary

0.87

ĸļ

0.84

ordering

0.82

 confir

0.81

 millenn

0.76

 meals

0.75

Activations Density 0.014%

phrases related to giving orders or instructions

instances of the word "ordered."

No Comments

No Known Activations