INDEX

Explanations

the name "Carson."

oai_token-act-pair · gpt-3.5-turbo

the name "Carson" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

lihood

-0.76

LAB

-0.69

manship

-0.66

âĸ¬âĸ¬

-0.65

hare

-0.63

flu

-0.61

teenth

-0.60

hh

-0.59

eering

-0.58

ties

-0.58

POSITIVE LOGITS

agher

1.12

illo

1.06

ieri

0.92

uth

0.91

 Daly

0.90

icum

0.90

atell

0.89

aughs

0.88

abis

0.88

 Rica

0.88

Activations Density 0.094%

the name "Carson."

the name "Carson" and its variations

No Comments

No Known Activations