INDEX

Explanations

phrases related to bundling or grouping various items together

oai_token-act-pair · gpt-3.5-turbo

references to bundles or grouped items

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

pez

-0.90

inel

-0.85

essee

-0.76

uria

-0.75

orgetown

-0.74

ilipp

-0.72

nesota

-0.72

cale

-0.71

orem

-0.71

throp

-0.71

POSITIVE LOGITS

 bundle

1.07

 bundles

1.00

 bund

0.96

undle

0.94

 bundled

0.80

 Bundle

0.79

 Breaker

0.73

halla

0.72

 containing

0.71

 Bund

0.67

Activations Density 0.033%

phrases related to bundling or grouping various items together

references to bundles or grouped items

No Comments

No Known Activations