INDEX

Explanations

words related to extensions or additional parts, often used in contexts like technology or physical objects

oai_token-act-pair · gpt-3.5-turbo

references to extensions 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 @ 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

iard

-0.85

\":

-0.85

icial

-0.77

kie

-0.76

-0.75

ivan

-0.75

ãĥ£

-0.74

hari

-0.73

rooms

-0.71

lins

-0.71

POSITIVE LOGITS

 cords

0.99

 cord

0.87

 extensions

0.87

 extension

0.81

 ende

0.74

 applic

0.70

 servicing

0.69

 therap

0.69

 validity

0.68

 maturity

0.68

Activations Density 0.025%

words related to extensions or additional parts, often used in contexts like technology or physical objects

references to extensions in various contexts

No Comments

No Known Activations