INDEX

Explanations

names of individuals or locations with the letters "z" or "k"

oai_token-act-pair · gpt-3.5-turbo

occurrences of specific letters or characters in words

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

 priceless

-0.77

_-

-0.72

 innocence

-0.64

 paradise

-0.63

 distraction

-0.60

 Paradise

-0.60

 wrath

-0.59

 hate

-0.56

 oppos

-0.56

 supernatural

-0.55

POSITIVE LOGITS

inski

1.05

anski

0.96

ynski

0.95

zynski

0.95

ety

0.91

owski

0.91

zb

0.87

owicz

0.87

oslav

0.85

ovsky

0.85

Activations Density 0.124%

names of individuals or locations with the letters "z" or "k"

occurrences of specific letters or characters in words

No Comments

No Known Activations