INDEX

Explanations

programming examples and code snippets

oai_token-act-pair · gpt-3.5-turbo

references to examples in a technical or instructional context

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

 mathemat

-0.86

 millenn

-0.85

vation

-0.84

ternity

-0.83

olulu

-0.83

ensibly

-0.80

reditary

-0.77

emetery

-0.77

ategory

-0.75

ailability

-0.74

POSITIVE LOGITS

 illustrating

0.75

 dummy

0.75

 Lily

0.73

hetical

0.71

wcsstore

0.70

 CLSID

0.70

 demonstrating

0.69

 subp

0.69

 examples

0.67

 Example

0.65

Activations Density 0.031%

programming examples and code snippets

references to examples in a technical or instructional context

No Comments

No Known Activations