INDEX

Explanations

numbers representing specific identifiers or values

oai_token-act-pair · gpt-3.5-turbo

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

istically

-0.77

estine

-0.76

holder

-0.75

think

-0.69

 Sands

-0.68

leck

-0.68

owicz

-0.67

uyomi

-0.67

arger

-0.62

anke

-0.60

POSITIVE LOGITS

mph

1.02

 ILCS

1.00

dB

0.89

mph

0.81

dB

0.81

0.77

é¾

0.77

0.76

rup

0.73

artment

0.72

Activations Density 0.046%

numbers representing specific identifiers or values

No Comments

No Known Activations