INDEX

Explanations

code snippets related to handling data and functions in a programming context

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and structural elements in code or text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ghan

-0.72

Tube

-0.71

amiya

-0.66

.–

-0.64

ometimes

-0.64

zbek

-0.64

icultural

-0.64

ogie

-0.62

ymph

-0.62

ochond

-0.62

POSITIVE LOGITS

 sizeof

1.04

 NULL

1.03

...)

0.99

 false

0.98

 args

0.96

nil

0.94

 lambda

0.93

0.92

"\

0.91

 None

0.91

Activations Density 0.031%

code snippets related to handling data and functions in a programming context

punctuation marks and structural elements in code or text

No Comments

No Known Activations