INDEX

Explanations

specific programming functions and tools within a codebase

oai_token-act-pair · gpt-3.5-turbo

phrases that define or describe functions and their attributes in programming 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

STE

-0.62

UGH

-0.62

spect

-0.59

 Cape

-0.59

 waning

-0.59

 Situation

-0.58

 Confederation

-0.58

 wounding

-0.57

oubted

-0.56

 Sioux

-0.55

POSITIVE LOGITS

 resembles

0.90

 corresponds

0.89

 enables

0.88

 helps

0.87

 allows

0.87

 converts

0.86

 specializes

0.85

 provides

0.84

 attaches

0.84

 translates

0.84

Activations Density 0.259%

specific programming functions and tools within a codebase

phrases that define or describe functions and their attributes in programming contexts

No Comments

No Known Activations