INDEX

Explanations

instances of the word "arrow"

oai_token-act-pair · gpt-3.5-turbo

references to arrows or arrow-related imagery

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

ĸļ

-0.88

oppable

-0.69

ĨĴ

-0.68

inen

-0.67

zsche

-0.64

hya

-0.63

 Marxism

-0.63

 aloud

-0.62

urity

-0.62

ometimes

-0.61

POSITIVE LOGITS

head

1.11

heads

1.07

heading

0.92

 arrow

0.92

 arrows

0.89

smith

0.82

 prope

0.79

fish

0.78

asso

0.78

headed

0.78

Activations Density 0.039%

instances of the word "arrow"

references to arrows or arrow-related imagery

No Comments

No Known Activations