INDEX

Explanations

words related to people or places, possibly focusing on specific individuals or locations

oai_token-act-pair · gpt-3.5-turbo

high-frequency occurrences of the substring "av"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Turing

-0.77

sofar

-0.69

utenant

-0.68

fog

-0.67

 poppy

-0.65

tug

-0.65

 unfor

-0.65

 handy

-0.65

 porous

-0.65

cold

-0.64

POSITIVE LOGITS

av

1.20

irus

1.11

oided

1.02

ascular

1.01

atars

1.00

ille

1.00

arro

1.00

itus

0.97

atar

0.97

irtual

0.96

Activations Density 0.009%

words related to people or places, possibly focusing on specific individuals or locations

high-frequency occurrences of the substring "av"

No Comments

No Known Activations