INDEX

Explanations

mention of locations or events where something significant happened

oai_token-act-pair · gpt-3.5-turbo

the phrase "at" indicating specific times or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sense

-0.59

rue

-0.59

gypt

-0.57

theless

-0.57

emonic

-0.54

rench

-0.53

vernment

-0.53

zip

-0.53

ertodd

-0.52

renches

-0.52

POSITIVE LOGITS

at

2.01

at

1.08

At

1.06

At

1.03

AT

0.91

 during

0.88

on

0.80

 around

0.79

 anywhere

0.78

in

0.76

Activations Density 0.211%

mention of locations or events where something significant happened

the phrase "at" indicating specific times or locations

No Comments

No Known Activations