INDEX

Explanations

proper nouns, particularly names of individuals or entities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "V" in various contexts

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

manship

-0.77

ãĤ´ãĥ³

-0.71

ãĥ³ãĤ¸

-0.67

keeping

-0.67

 mats

-0.66

 medi

-0.65

 tackling

-0.65

 shortened

-0.65

 sidebar

-0.65

 untreated

-0.65

POSITIVE LOGITS

arsity

1.32

ancouver

1.28

III

1.21

oodoo

1.18

ampire

1.16

ortex

1.15

ulture

1.14

ampires

1.13

iolet

1.13

anguard

1.12

Activations Density 0.032%

proper nouns, particularly names of individuals or entities

occurrences of the letter "V" in various contexts

No Comments

No Known Activations