INDEX

Explanations

mentions of tea-related items and activities

oai_token-act-pair · gpt-3.5-turbo

references to tea in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

izons

-0.77

entric

-0.77

ities

-0.77

phis

-0.76

nesota

-0.75

ibilities

-0.73

osure

-0.73

 WATCHED

-0.71

ividual

-0.69

alities

-0.69

POSITIVE LOGITS

tea

1.05

 towels

1.01

 towel

0.98

 drinkers

0.93

Tea

0.91

quila

0.90

 kettle

0.87

Tea

0.86

 cups

0.83

 flask

0.82

Activations Density 0.008%

mentions of tea-related items and activities

references to tea in various contexts

No Comments

No Known Activations