INDEX

Explanations

proper nouns or names that appear in multiple contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "appears" and related terms indicating frequency and presence in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 dilig

-0.70

Progress

-0.65

acion

-0.60

ustom

-0.60

cise

-0.59

achine

-0.58

 Winning

-0.58

ugu

-0.57

rug

-0.56

cig

-0.56

POSITIVE LOGITS

 prominently

1.29

 elsewhere

1.02

 mentioned

1.01

 anywhere

1.01

 appearing

1.00

 therein

0.97

 uttered

0.96

mentioned

0.93

 referenced

0.93

 reapp

0.91

Activations Density 0.496%

proper nouns or names that appear in multiple contexts

occurrences of the phrase "appears" and related terms indicating frequency and presence in various contexts

No Comments

No Known Activations