INDEX

Explanations

mentions of locations or events related to a specific context or topic

oai_token-act-pair · gpt-3.5-turbo

the occurrence of the word "the" in different contexts

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

ipolar

-0.74

interrupted

-0.72

 eleph

-0.65

lessly

-0.64

usher

-0.63

 pressures

-0.63

iqueness

-0.61

antha

-0.61

etheless

-0.61

olicy

-0.59

POSITIVE LOGITS

brate

1.43

brates

1.32

ller

1.18

llers

1.13

achers

1.12

achable

1.10

levision

1.09

legraph

1.09

aching

1.03

legram

1.02

Activations Density 0.017%

mentions of locations or events related to a specific context or topic

the occurrence of the word "the" in different contexts

No Comments

No Known Activations