INDEX

Explanations

possessive pronouns indicating ownership or connection to something

oai_token-act-pair · gpt-3.5-turbo

possessive pronouns indicating ownership or affiliation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

iti

-0.84

ocument

-0.83

river

-0.82

ILE

-0.80

mire

-0.77

ĳå£«

-0.76

haus

-0.76

atever

-0.74

gap

-0.73

tree

-0.72

POSITIVE LOGITS

own

1.77

 penchant

1.25

 willingness

1.24

 inability

1.19

 ability

1.15

 propensity

1.12

 favourite

1.08

 unwillingness

1.04

selves

1.03

OWN

1.02

Activations Density 0.164%

possessive pronouns indicating ownership or connection to something

possessive pronouns indicating ownership or affiliation

No Comments

No Known Activations