INDEX

Explanations

References to specific values, parameters, and variables used in computer programming

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the existence or state of being

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

ventures

-0.88

 IMAGES

-0.75

iasco

-0.75

Enlarge

-0.72

edin

-0.71

 woes

-0.70

rums

-0.69

few

-0.68

dates

-0.67

stories

-0.66

POSITIVE LOGITS

 equivalent

1.09

 preferable

1.09

 shorthand

1.02

 considered

1.02

 identical

0.99

omorphic

0.99

 substituted

0.98

 interpreted

0.97

 defined

0.97

 omitted

0.96

Activations Density 0.170%

References to specific values, parameters, and variables used in computer programming

phrases indicating the existence or state of being

No Comments

No Known Activations