INDEX

Explanations

numerical values

oai_token-act-pair · gpt-3.5-turbo

numbers, particularly those formatted as numerical values or codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

orem

-0.80

owered

-0.74

amaru

-0.73

hed

-0.71

iple

-0.70

ãĥ´ãĤ¡

-0.69

herer

-0.68

atis

-0.68

herty

-0.68

aur

-0.66

POSITIVE LOGITS

nd

1.28

Â¯Â¯

0.82

0.77

0.76

nces

0.75

rd

0.73

mph

0.71

pine

0.71

een

0.70

lake

0.69

Activations Density 0.043%

numerical values

numbers, particularly those formatted as numerical values or codes

No Comments

No Known Activations