INDEX

Explanations

terms related to invoking or invoking a concept or right

oai_token-act-pair · gpt-3.5-turbo

the term "invoke" and its variations in the context of legal, constitutional, or formal usage

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

cas

-0.83

ians

-0.75

>>\

-0.75

Ł

-0.75

Īè

-0.74

jri

-0.69

ago

-0.69

md

-0.63

¯

-0.63

±

-0.62

POSITIVE LOGITS

 invoked

0.88

 invoking

0.87

 invoke

0.86

 caution

0.83

unction

0.81

uncture

0.74

 pardon

0.72

 warnings

0.72

 invocation

0.71

oked

0.71

Activations Density 0.019%

terms related to invoking or invoking a concept or right

the term "invoke" and its variations in the context of legal, constitutional, or formal usage

No Comments

No Known Activations