INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

locations or contexts described in a narrative

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

ÂłÂłÂłÂłÂłÂłÂłÂł

-0.76

rolet

-0.70

yi

-0.70

ets

-0.66

ocker

-0.63

agers

-0.62

ÂłÂłÂł

-0.61

wu

-0.60

 Beasts

-0.57

]);

-0.56

POSITIVE LOGITS

upon

1.33

abouts

1.28

soever

1.16

fore

1.01

ver

0.76

ãĥ¯ãĥ³

0.72

 houses

0.71

with

0.70

artment

0.69

abama

0.68

Activations Density 0.070%

locations or places

locations or contexts described in a narrative

No Comments

No Known Activations