INDEX

Explanations

IDs or identification numbers in textual content

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "ID" 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

theless

-0.79

noon

-0.74

uala

-0.73

~~~~~~~~~~~~~~~~

-0.72

Church

-0.71

gha

-0.71

Lago

-0.70

uckland

-0.70

frey

-0.69

 decad

-0.68

POSITIVE LOGITS

ID

3.88

IDs

2.89

ID

2.13

 identification

1.93

 Identification

1.66

IDs

1.53

id

1.48

 identifier

1.46

Id

1.45

Id

1.44

Activations Density 0.017%

IDs or identification numbers in textual content

occurrences of the term "ID" in various contexts

No Comments

No Known Activations