INDEX

Explanations

instances of locations based on the state abbreviation "FL"

oai_token-act-pair · gpt-3.5-turbo

mentions of the state of Florida

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

selves

-0.79

thodox

-0.76

uyomi

-0.69

nor

-0.68

ãĥīãĥ©ãĤ´ãĥ³

-0.68

bell

-0.64

terday

-0.64

 familiar

-0.62

 Built

-0.61

 ç¥ŀ

-0.61

POSITIVE LOGITS

ESH

1.00

UX

0.99

OW

0.97

owship

0.97

YING

0.96

FL

0.93

oyd

0.90

OWER

0.90

TF

0.88

ibrary

0.88

Activations Density 0.005%

instances of locations based on the state abbreviation "FL"

mentions of the state of Florida

No Comments

No Known Activations