INDEX

Explanations

words related to ingredients and cooking instructions, especially celery

oai_token-act-pair · gpt-3.5-turbo

references to celery within various contexts

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

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

ulated

-0.79

ulative

-0.77

eston

-0.75

PF

-0.74

ested

-0.69

ifier

-0.68

embed

-0.68

ers

-0.66

ulating

-0.64

Winged

-0.64

POSITIVE LOGITS

flies

0.93

llan

0.88

tery

0.86

nces

0.83

onica

0.76

ea

0.76

oire

0.75

yy

0.73

 shelves

0.71

utical

0.71

Activations Density 0.061%

words related to ingredients and cooking instructions, especially celery

references to celery within various contexts

No Comments

No Known Activations