INDEX

Explanations

indefinite articles followed by nouns

oai_token-act-pair · gpt-3.5-turbo

phrases that quantify or reference amounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

icism

-0.89

matter

-0.83

brance

-0.82

cation

-0.80

ileaks

-0.79

ernaut

-0.76

terness

-0.74

antry

-0.74

rack

-0.72

nesday

-0.72

POSITIVE LOGITS

 constants

1.11

 exceptions

1.04

types

1.04

 indications

1.04

 instances

0.94

 representations

0.93

 batches

0.93

 clauses

0.93

 roles

0.92

 winners

0.92

Activations Density 0.277%

indefinite articles followed by nouns

phrases that quantify or reference amounts

No Comments

No Known Activations