INDEX

Explanations

phrases related to recipes and cooking instructions

oai_token-act-pair · gpt-3.5-turbo

instructions and actions related to cooking or food preparation

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

 funer

-0.83

abilia

-0.76

ighth

-0.71

 Cele

-0.71

 souven

-0.69

 relics

-0.69

 tattoos

-0.67

 dearly

-0.65

dq

-0.65

dfx

-0.65

POSITIVE LOGITS

Prep

0.85

ilst

0.85

 blender

0.83

 skillet

0.78

METHOD

0.74

Method

0.73

 oven

0.73

 parchment

0.71

illon

0.70

Instant

0.70

Activations Density 0.128%

phrases related to recipes and cooking instructions

instructions and actions related to cooking or food preparation

No Comments

No Known Activations