INDEX

Explanations

names or references to individuals or entities, especially those with the letters 'id'

oai_token-act-pair · gpt-3.5-turbo

instances of the word "ID" or related identifiers 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 @ 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

bilt

-0.91

andise

-0.85

=-=-

-0.72

 Seym

-0.72

estern

-0.69

 Remem

-0.63

 biscuits

-0.61

izabeth

-0.60

£ı

-0.60

 Nova

-0.59

POSITIVE LOGITS

irection

1.18

ividual

1.12

iots

1.05

eways

0.97

irect

0.96

aniel

0.93

imensional

0.92

der

0.91

ocument

0.91

gets

0.91

Activations Density 0.029%

names or references to individuals or entities, especially those with the letters 'id'

instances of the word "ID" or related identifiers in various contexts

No Comments

No Known Activations