INDEX

Explanations

the word "got" at various activation levels

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "got" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

velt

-0.62

 vein

-0.59

amd

-0.59

Protect

-0.57

 Archdemon

-0.57

trust

-0.57

mare

-0.56

deen

-0.55

die

-0.54

orable

-0.54

POSITIVE LOGITS

rid

1.25

 acquainted

1.01

 permission

0.89

cloneembedreportprint

0.88

 underway

0.88

 lucky

0.87

cha

0.80

 entangled

0.78

bog

0.77

 caught

0.76

Activations Density 0.110%

the word "got" at various activation levels

instances of the verb "got" and its variations

No Comments

No Known Activations