INDEX

Explanations

phrases indicating the addition or inclusion of something to a list, group, or collection

oai_token-act-pair · gpt-3.5-turbo

mentions related to lists and additions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

actionDate

-0.77

theless

-0.68

glers

-0.68

hots

-0.68

fw

-0.67

 ______

-0.66

ï¸

-0.65

RESULTS

-0.65

Ô

-0.64

][

-0.64

POSITIVE LOGITS

 repertoire

1.00

 fray

0.95

 list

0.94

 equation

0.93

 ranks

0.92

 arsenal

0.85

 existing

0.80

 reperto

0.79

 forefront

0.77

 regimen

0.77

Activations Density 0.175%

phrases indicating the addition or inclusion of something to a list, group, or collection

mentions related to lists and additions

No Comments

No Known Activations