INDEX

Explanations

phrases related to long-term duration or permanence

oai_token-act-pair · gpt-3.5-turbo

references to long-term implications or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ismo

-0.69

dain

-0.69

HCR

-0.68

SHIP

-0.66

uala

-0.66

stellar

-0.66

osponsors

-0.64

inia

-0.62

VERTISEMENT

-0.62

illon

-0.61

POSITIVE LOGITS

est

1.07

liest

0.97

hest

0.88

 side

0.87

iest

0.86

 term

0.84

 confines

0.83

 assumption

0.81

 aftermath

0.79

end

0.77

Activations Density 0.138%

phrases related to long-term duration or permanence

references to long-term implications or consequences

No Comments

No Known Activations