INDEX

Explanations

positive adjectives

oai_token-act-pair · gpt-3.5-turbo

positive descriptors and evaluations of quality

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

meric

-0.69

HQ

-0.66

mere

-0.65

pora

-0.65

berto

-0.61

minecraft

-0.61

atars

-0.60

uala

-0.60

Peb

-0.58

ubi

-0.58

POSITIVE LOGITS

 indeed

0.78

 nails

0.76

 sounding

0.74

nered

0.68

 understatement

0.68

 wound

0.67

 nowadays

0.61

 spoiler

0.61

(>

0.61

 sailing

0.61

Activations Density 0.115%

positive adjectives

positive descriptors and evaluations of quality

No Comments

No Known Activations