INDEX

Explanations

sentences or phrases end with periods

oai_token-act-pair · gpt-3.5-turbo

sentences that convey conclusive or definitive statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

thal

-0.75

awed

-0.74

 quir

-0.72

ady

-0.72

eteenth

-0.71

 disemb

-0.70

zel

-0.69

anka

-0.66

onding

-0.65

 heir

-0.64

POSITIVE LOGITS

 âĢ¦"

1.20

 Whoever

1.18

 Especially

1.15

 Hopefully

1.13

 Otherwise

1.13

 Everybody

1.13

 Therefore

1.13

 Obviously

1.12

 Somebody

1.10

 They

1.08

Activations Density 0.329%

sentences or phrases end with periods

sentences that convey conclusive or definitive statements

No Comments

No Known Activations