INDEX

Explanations

quantities or numerical terms related to groups or collections of people or objects

oai_token-act-pair · gpt-3.5-turbo

references to quantity and groups of people or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Akin

-0.78

 Weir

-0.74

 Dirk

-0.64

cy

-0.64

matter

-0.63

ãĥ³

-0.63

ENSE

-0.63

Ì

-0.63

 Wraith

-0.62

ptroller

-0.62

POSITIVE LOGITS

 finalists

0.83

 exempted

0.80

 earners

0.79

 phenomena

0.76

 factors

0.76

 beneficiaries

0.74

 additions

0.73

 nationwide

0.73

ynski

0.72

 manifestations

0.72

Activations Density 0.152%

quantities or numerical terms related to groups or collections of people or objects

references to quantity and groups of people or items

No Comments

No Known Activations