INDEX

Explanations

words related to data formats, particularly focusing on JSON

oai_token-act-pair · gpt-3.5-turbo

references to JSON data format and its usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ners

-0.74

ndra

-0.71

itism

-0.70

 Dull

-0.68

________________

-0.68

forums

-0.66

higher

-0.66

ggies

-0.65

istas

-0.64

flies

-0.64

POSITIVE LOGITS

RPC

0.86

 encoded

0.83

 JSON

0.80

JSON

0.78

icter

0.77

 formatted

0.76

 converter

0.76

 schema

0.72

 json

0.71

dump

0.69

Activations Density 0.021%

words related to data formats, particularly focusing on JSON

references to JSON data format and its usage

No Comments

No Known Activations