INDEX

Explanations

personal pronouns related to self-reflection

oai_token-act-pair · gpt-3.5-turbo

references to the pronoun "you."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

¿½

-0.73

assembly

-0.66

 Thomson

-0.65

stadt

-0.60

EStream

-0.58

pty

-0.57

 Commerce

-0.57

 Innocent

-0.56

shows

-0.56

POSITIVE LOGITS

're

1.80

've

1.52

'll

1.32

'd

1.10

 yourselves

1.07

owe

1.07

 know

1.06

are

1.04

 yourself

1.02

ngth

1.02

Activations Density 0.247%

personal pronouns related to self-reflection

references to the pronoun "you."

No Comments

No Known Activations