INDEX

Explanations

actions or attributes related to strength, power, and intensity

oai_token-act-pair · gpt-3.5-turbo

descriptive words and phrases indicating intensity or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Semin

-0.62

pressed

-0.61

ylum

-0.60

 Siber

-0.60

uve

-0.58

izations

-0.58

Reference

-0.57

vals

-0.55

ples

-0.55

activated

-0.54

POSITIVE LOGITS

 tremend

0.78

igious

0.76

entimes

0.75

ernaut

0.71

weed

0.70

gie

0.65

ËĪ

0.64

Â¯Â¯Â¯Â¯

0.64

emonic

0.64

unct

0.62

Activations Density 0.442%

actions or attributes related to strength, power, and intensity

descriptive words and phrases indicating intensity or significance

No Comments

No Known Activations