INDEX

Explanations

words related to physical descriptions or attributes

oai_token-act-pair · gpt-3.5-turbo

the word "on" 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 @ 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

TPP

-0.90

QB

-0.78

INESS

-0.77

ACTED

-0.73

PDF

-0.73

amus

-0.73

MODE

-0.72

soDeliveryDate

-0.70

ELF

-0.69

Ur

-0.69

POSITIVE LOGITS

 behalf

1.32

coming

1.04

etime

1.03

erous

1.01

shore

0.99

sets

0.98

eday

0.91

yx

0.90

 occasion

0.85

 rooft

0.85

Activations Density 0.220%

words related to physical descriptions or attributes

the word "on" in various contexts

No Comments

No Known Activations