INDEX

Explanations

personal pronouns followed by verbs or observations, particularly related to social media and politics

oai_token-act-pair · gpt-3.5-turbo

repeated pronouns and expressions of knowledge or belief

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

 disappearing

-0.65

 Restoration

-0.64

 Effective

-0.63

 Blessing

-0.61

 Reborn

-0.60

 Plum

-0.58

forms

-0.58

 Delicious

-0.57

-0.56

 Refuge

-0.56

POSITIVE LOGITS

 wonder

1.02

 wish

0.96

 hear

0.96

 sympath

0.95

 understand

0.95

 know

0.95

 imag

0.92

 feel

0.91

 empath

0.90

 realise

0.90

Activations Density 0.415%

personal pronouns followed by verbs or observations, particularly related to social media and politics

repeated pronouns and expressions of knowledge or belief

No Comments

No Known Activations