INDEX

Explanations

words related to planning and coordination

oai_token-act-pair · gpt-3.5-turbo

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

sac

-0.72

cia

-0.66

ritical

-0.66

croft

-0.63

ijk

-0.61

 afore

-0.61

 Americas

-0.61

antha

-0.58

si

-0.58

bal

-0.57

POSITIVE LOGITS

 frantically

0.70

 furiously

0.69

 ducks

0.67

ITAL

0.65

irection

0.64

igated

0.62

ļé

0.61

IUM

0.60

ÃįÃį

0.60

 renov

0.60

Activations Density 0.252%

words related to planning and coordination

No Comments

No Known Activations