INDEX

Explanations

contractions of 'is' with subsequent words

oai_token-act-pair · gpt-3.5-turbo

expressions that indicate affirmation or acknowledgment

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

bies

-0.68

 peasants

-0.67

izens

-0.65

 ropes

-0.65

 mull

-0.64

 rate

-0.61

 coasts

-0.60

luaj

-0.60

 throats

-0.60

 faults

-0.58

POSITIVE LOGITS

rael

0.79

 Mahjong

0.74

claimer

0.74

bourg

0.73

nt

0.71

quickShipAvailable

0.70

 definitely

0.69

rame

0.67

hemy

0.67

Ĥ¬

0.66

Activations Density 0.192%

contractions of 'is' with subsequent words

expressions that indicate affirmation or acknowledgment

No Known Activations