INDEX

Explanations

specific programming terms and actions related to coding functions and logic

oai_token-act-pair · gpt-3.5-turbo

programming concepts related to functions and their inputs/outputs

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

-0.96

soever

-0.78

CLASSIFIED

-0.72

aeda

-0.70

OSH

-0.69

ortment

-0.67

aucuses

-0.66

uminati

-0.65

ADA

-0.65

emale

-0.64

POSITIVE LOGITS

0.90

['

0.82

!=

0.78

==

0.77

["

0.73

+=

0.73

obj

0.72

=>

0.71

Value

0.70

Dir

0.70

Activations Density 0.114%

specific programming terms and actions related to coding functions and logic

programming concepts related to functions and their inputs/outputs

No Comments

No Known Activations