INDEX

Explanations

words related to legal or formal terms

oai_token-act-pair · gpt-3.5-turbo

words related to judgment or evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hess

-0.76

 Grayson

-0.72

 Cheong

-0.70

ingham

-0.67

hyde

-0.67

 Highlands

-0.65

 Sutherland

-0.64

enhagen

-0.62

 Shepherd

-0.62

 Trace

-0.61

POSITIVE LOGITS

 propos

0.64

 pestic

0.64

 predec

0.64

 comprom

0.62

manent

0.61

 bureaucr

0.61

abor

0.60

 embassies

0.59

 taxp

0.59

anc

0.59

Activations Density 0.535%

words related to legal or formal terms

words related to judgment or evaluation

No Comments

No Known Activations