INDEX

Explanations

proper nouns related to people and places

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names associated with individuals

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 progress

-0.69

ipeg

-0.68

 correctness

-0.64

pts

-0.62

strous

-0.60

FIX

-0.59

 selection

-0.59

 prompt

-0.58

 Selection

-0.57

omen

-0.57

POSITIVE LOGITS

Jr

1.34

Sr

1.16

aka

1.06

Jr

0.96

who

0.93

who

0.93

QC

0.90

PhD

0.88

whose

0.88

 whose

0.87

Activations Density 0.283%

proper nouns related to people and places

proper nouns and names associated with individuals

No Comments

No Known Activations