INDEX

Explanations

differences or variations in attributes or characteristics

oai_token-act-pair · gpt-3.5-turbo

terms related to individual and group differences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

latest

-0.71

amaz

-0.68

 Revelations

-0.66

renheit

-0.66

sat

-0.65

adra

-0.65

ãĥ¼ãĥ³

-0.65

mington

-0.65

asus

-0.63

nit

-0.63

POSITIVE LOGITS

 influencing

1.15

 underlying

1.15

 affecting

1.13

 arising

1.02

pace

1.01

hips

0.99

 inherent

0.99

 favoring

0.98

ystem

0.98

 involving

0.97

Activations Density 0.284%

differences or variations in attributes or characteristics

terms related to individual and group differences

No Comments

No Known Activations