INDEX

Explanations

mentions of cocktails

oai_token-act-pair · gpt-3.5-turbo

references to cocktails and related terms

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

Not in Any Lists

No Comments

Negative Logits

 Parenthood

-0.87

NCT

-0.76

Filename

-0.74

ledged

-0.72

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.70

closed

-0.68

parent

-0.68

UCH

-0.68

mental

-0.67

thritis

-0.67

POSITIVE LOGITS

 cocktail

1.16

 cocktails

1.11

 conco

1.08

 waitress

1.07

 drinks

0.97

 drink

0.96

cohol

0.86

 syrup

0.85

 beverage

0.84

 champagne

0.84

Activations Density 0.025%

mentions of cocktails

references to cocktails and related terms

No Comments

No Known Activations