INDEX

Explanations

words related to mammalian biology

oai_token-act-pair · gpt-3.5-turbo

references to mammals and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

iffe

-0.87

uler

-0.80

inning

-0.78

mire

-0.76

room

-0.71

rapnel

-0.71

iner

-0.70

mir

-0.69

outer

-0.69

acher

-0.69

POSITIVE LOGITS

 mammals

1.18

 mammal

1.06

cules

1.03

 reptiles

1.00

 carniv

0.99

 species

0.98

brates

0.97

 primates

0.94

osaurs

0.92

 mammalian

0.87

Activations Density 0.027%

words related to mammalian biology

references to mammals and related terminology

No Comments

No Known Activations