INDEX

Explanations

the word "ho" with varying levels of activation

oai_token-act-pair · gpt-3.5-turbo

the word "ho" in various contexts and forms

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

Zig

-0.70

 result

-0.68

 Flavoring

-0.66

 divorce

-0.66

 resolutions

-0.64

 Sheldon

-0.64

 Calais

-0.64

 Dent

-0.64

 Silver

-0.63

 results

-0.60

POSITIVE LOGITS

ho

4.65

Ho

1.74

hoe

1.68

hi

1.62

HO

1.61

hops

1.57

hop

1.57

hu

1.55

ha

1.47

hin

1.41

Activations Density 0.010%

the word "ho" with varying levels of activation

the word "ho" in various contexts and forms

No Comments

No Known Activations