INDEX

Explanations

phrases or clauses starting with "anything that" or "everything that"

oai_token-act-pair · gpt-3.5-turbo

phrases that begin with "that" indicating specificity or clarification

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

mi

-0.70

aq

-0.70

ply

-0.67

roth

-0.65

gur

-0.65

pling

-0.62

lying

-0.60

ãĥ¥

-0.60

united

-0.60

roy

-0.59

POSITIVE LOGITS

 happens

1.17

 happened

1.09

 occurs

0.99

 arose

0.97

 transpired

0.93

 happen

0.92

 affects

0.91

 entails

0.91

 happ

0.91

 separates

0.90

Activations Density 0.162%

phrases or clauses starting with "anything that" or "everything that"

phrases that begin with "that" indicating specificity or clarification

No Comments

No Known Activations