INDEX

Explanations

names of individuals or characters

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

iculty

-0.79

antry

-0.79

istry

-0.74

hedral

-0.74

itizen

-0.73

imates

-0.71

rants

-0.71

ropy

-0.70

fulness

-0.70

ribute

-0.69

POSITIVE LOGITS

thal

0.81

rities

0.80

ously

0.73

ova

0.69

 Rove

0.66

vow

0.66

eers

0.65

 neuron

0.64

Osw

0.63

ocal

0.61

Activations Density 0.104%

names of individuals or characters

proper nouns, specifically names of individuals

No Comments

No Known Activations