INDEX

Explanations

names or words related to people or companies, particularly ones starting with 'Di'

oai_token-act-pair · gpt-3.5-turbo

proper nouns and brand names related to businesses or organizations

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

ãĤ´ãĥ³

-0.85

CLASS

-0.69

 envy

-0.66

 responsiveness

-0.64

Ô

-0.63

 Adin

-0.63

 srfAttach

-0.62

 conspicuous

-0.61

wards

-0.59

 corrosion

-0.59

POSITIVE LOGITS

pora

1.07

nih

0.98

cious

0.84

etus

0.84

ritical

0.83

ibur

0.81

arb

0.79

ect

0.79

liction

0.78

asio

0.76

Activations Density 0.048%

names or words related to people or companies, particularly ones starting with 'Di'

proper nouns and brand names related to businesses or organizations

No Comments

No Known Activations