INDEX

Explanations

references to the self or personal interactions

oai_token-act-pair · gpt-3.5-turbo

the pronoun "me" in various contexts, indicating a focus on personal identity and self-perception

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ulton

-0.69

atlantic

-0.68

emic

-0.68

naissance

-0.65

etheus

-0.64

iens

-0.63

ories

-0.63

Atlantic

-0.63

-)

-0.63

icion

-0.63

POSITIVE LOGITS

adows

0.86

 personally

0.83

imei

0.81

selves

0.76

adow

0.75

 verbally

0.73

atic

0.73

self

0.72

 uncond

0.72

zzo

0.72

Activations Density 0.183%

references to the self or personal interactions

the pronoun "me" in various contexts, indicating a focus on personal identity and self-perception

No Comments

No Known Activations