INDEX

Explanations

suggestions or actions that can be taken

oai_token-act-pair · gpt-3.5-turbo

phrases related to actions or measures being taken

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

fre

-0.77

antha

-0.70

inately

-0.68

 Faul

-0.66

phe

-0.65

 reused

-0.65

 Aless

-0.64

space

-0.64

 Phant

-0.64

ench

-0.63

POSITIVE LOGITS

 corrective

1.02

 ACTIONS

0.98

 actions

0.93

 steps

0.93

 inaction

0.87

 concerted

0.85

 decisively

0.85

GBT

0.84

 toward

0.82

 Steps

0.81

Activations Density 0.230%

suggestions or actions that can be taken

phrases related to actions or measures being taken

No Comments

No Known Activations