INDEX

Explanations

technical terms or words related to programming and coding

oai_token-act-pair · gpt-3.5-turbo

keywords related to advertisements

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

Bug

-0.89

Thumbnail

-0.82

Alert

-0.79

Aren

-0.79

Reloaded

-0.77

Poor

-0.76

Suggest

-0.76

Wire

-0.74

Gene

-0.74

Pac

-0.74

POSITIVE LOGITS

 Misty

0.66

İĭ

0.66

xual

0.66

,"

0.65

 sher

0.64

 JUSTICE

0.63

ŃĶ

0.63

chnology

0.62

 inclusive

0.62

Activations Density 0.080%

technical terms or words related to programming and coding

keywords related to advertisements

No Comments

No Known Activations