INDEX

Explanations

proper nouns related to the name "Sha"

oai_token-act-pair · gpt-3.5-turbo

names and references to individuals associated with a specific context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

akeru

-0.79

anova

-0.75

inally

-0.73

antically

-0.71

sburgh

-0.70

gerald

-0.70

antom

-0.69

roman

-0.68

tor

-0.68

pheus

-0.67

POSITIVE LOGITS

asar

0.78

izer

0.70

ough

0.69

eless

0.69

Kings

0.67

pless

0.67

urst

0.66

Sha

0.64

\\\\\\\\

0.64

pling

0.64

Activations Density 0.053%

proper nouns related to the name "Sha"

names and references to individuals associated with a specific context

No Comments

No Known Activations