INDEX

Explanations

locations or geographic features, particularly peaks or mountains

oai_token-act-pair · gpt-3.5-turbo

references to elevated landforms or geographical features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 bowel

-0.72

 Swarm

-0.63

Lug

-0.62

tarians

-0.62

urg

-0.61

 sidel

-0.61

 contribut

-0.61

actionDate

-0.61

 neurot

-0.61

party

-0.59

POSITIVE LOGITS

 Peaks

0.92

ciation

0.79

nown

0.78

lopp

0.78

scl

0.77

regon

0.77

ãĤ¤ãĥĪ

0.76

folios

0.75

iddles

0.75

paio

0.74

Activations Density 0.040%

locations or geographic features, particularly peaks or mountains

references to elevated landforms or geographical features

No Comments

No Known Activations