INDEX

Explanations

verbs or phrases related to actions directed towards a specific goal or target

oai_token-act-pair · gpt-3.5-turbo

phrases indicating intended actions or objectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Optional

-0.74

 hesitate

-0.69

minus

-0.69

wine

-0.67

zek

-0.67

NESS

-0.66

ledged

-0.66

wait

-0.65

asca

-0.65

owa

-0.65

POSITIVE LOGITS

 improving

1.68

 preventing

1.67

 preserving

1.63

 protecting

1.56

 combating

1.55

 ensuring

1.53

 reducing

1.51

 promoting

1.50

 restoring

1.50

 eliminating

1.50

Activations Density 0.191%

verbs or phrases related to actions directed towards a specific goal or target

phrases indicating intended actions or objectives

No Comments

No Known Activations