INDEX

Explanations

words or phrases related to spin-offs

oai_token-act-pair · gpt-3.5-turbo

instances of the word "spin" and its variations, indicating a focus on adaptations or reinterpretations of existing content

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

inances

-0.73

 Admir

-0.67

ermott

-0.67

avis

-0.65

 Commodore

-0.64

 Scores

-0.63

 Mellon

-0.63

 stakes

-0.63

inez

-0.61

ecause

-0.60

POSITIVE LOGITS

ners

1.41

 spin

0.95

eless

0.93

kered

0.91

wheel

0.86

ned

0.86

offs

0.86

rot

0.84

spin

0.83

lass

0.82

Activations Density 0.012%

words or phrases related to spin-offs

instances of the word "spin" and its variations, indicating a focus on adaptations or reinterpretations of existing content

No Comments

No Known Activations