INDEX

Explanations

places or geographic locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Land" in various contexts

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

 inhibitor

-0.77

uffy

-0.75

 inhibitors

-0.74

azine

-0.73

 slee

-0.71

apr

-0.71

abetic

-0.71

nc

-0.69

pn

-0.68

 dysph

-0.68

POSITIVE LOGITS

 Land

3.78

Land

2.80

 Lands

2.17

 land

2.04

land

1.80

 lands

1.47

LAND

1.40

 Landing

1.19

lands

1.18

 Forest

1.17

Activations Density 0.012%

places or geographic locations

occurrences of the word "Land" in various contexts

No Comments

No Known Activations