INDEX

Explanations

food items, specifically sandwiches

oai_token-act-pair · gpt-3.5-turbo

references to sandwiches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

tics

-0.90

orne

-0.76

mberg

-0.73

SPONSORED

-0.72

ibr

-0.67

aft

-0.67

ignty

-0.66

umen

-0.65

oln

-0.64

axis

-0.63

POSITIVE LOGITS

 sandwiches

1.12

wich

1.06

 sandwich

1.05

bowl

0.92

 Sandwich

0.88

 slices

0.86

eering

0.85

 salads

0.85

 tray

0.81

 salad

0.78

Activations Density 0.021%

food items, specifically sandwiches

references to sandwiches

No Comments

No Known Activations