INDEX

Explanations

words related to subcategories or subdivisions within a larger group or concept

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "sub" followed by numerical values

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

 Qiao

-0.79

ILLE

-0.76

 GOODMAN

-0.75

 Walker

-0.71

 Zurich

-0.70

 Muse

-0.69

 Lauder

-0.68

BILITY

-0.67

 Palmer

-0.67

 Cardinal

-0.67

POSITIVE LOGITS

missive

1.44

verting

1.26

mitter

1.24

sequent

1.19

sequently

1.18

mers

1.15

ordinate

1.13

continental

1.13

mits

1.12

mitt

1.12

Activations Density 0.015%

words related to subcategories or subdivisions within a larger group or concept

occurrences of the word "sub" followed by numerical values

No Comments

No Known Activations