INDEX

Explanations

technical phrases and terms related to software development

oai_token-act-pair · gpt-3.5-turbo

specific objects, identifiers, and technical terms related to programming or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

odox

-0.84

ãĤ±

-0.80

arious

-0.76

ãĥ¥

-0.69

Bloom

-0.67

ãĤ®

-0.67

bent

-0.66

ãĤ¤ãĥĪ

-0.66

Benz

-0.66

ãĥ´ãĤ¡

-0.66

POSITIVE LOGITS

 itself

0.73

 alone

0.64

 moniker

0.63

 plus

0.59

 deployment

0.58

 designation

0.58

 invocation

0.57

 initiative

0.57

 instance

0.57

 tenancy

0.57

Activations Density 0.762%

technical phrases and terms related to software development

specific objects, identifiers, and technical terms related to programming or technical contexts

No Comments

No Known Activations