INDEX

Explanations

verbs indicating completion or accomplishment

oai_token-act-pair · gpt-3.5-turbo

the word "done" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Reviewer

-0.80

olson

-0.78

ulates

-0.77

liner

-0.76

lights

-0.74

ussen

-0.74

anmar

-0.72

Demand

-0.67

dayName

-0.66

CVE

-0.66

POSITIVE LOGITS

pez

1.11

 differently

0.70

onga

0.70

 nothing

0.69

ggie

0.68

 administr

0.67

 away

0.66

omething

0.65

 homework

0.63

VIDIA

0.63

Activations Density 0.027%

verbs indicating completion or accomplishment

the word "done" in various contexts

No Comments

No Known Activations