INDEX

Explanations

proper nouns related to specific locations or events

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific names related to locations or events

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

 Citation

-0.69

 srfAttach

-0.68

 Affect

-0.67

 Veil

-0.67

 ACTIONS

-0.66

 Preferred

-0.65

Machine

-0.64

 Cells

-0.63

tnc

-0.62

 Mistress

-0.62

POSITIVE LOGITS

shire

0.96

coming

0.93

forth

0.87

ocal

0.85

ishing

0.85

enhagen

0.83

ines

0.83

ishment

0.82

ton

0.81

keye

0.80

Activations Density 0.111%

proper nouns related to specific locations or events

proper nouns and specific names related to locations or events

No Comments

No Known Activations