INDEX

Explanations

keywords related to computer programming, file operations, data frames, and technical instructions

oai_token-act-pair · gpt-3.5-turbo

references to military ranks and organizational structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Instr

-0.74

SPONSORED

-0.68

 lest

-0.64

 explan

-0.62

 undermin

-0.61

efficients

-0.61

 vulner

-0.60

 disadvant

-0.59

galitarian

-0.59

assies

-0.59

POSITIVE LOGITS

\":

0.70

PDATED

0.64

 Version

0.60

/-

0.59

)-

0.59

!--

0.59

==

0.58

ãĢĳ

0.58

 scanner

0.56

)/

0.56

Activations Density 0.091%

keywords related to computer programming, file operations, data frames, and technical instructions

references to military ranks and organizational structures

No Comments

No Known Activations