INDEX

Explanations

mentions of experimental or investigational procedures or studies

oai_token-act-pair · gpt-3.5-turbo

terms related to experimental research and studies

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

andra

-0.81

veland

-0.77

adr

-0.74

pered

-0.74

utra

-0.74

ETS

-0.74

cript

-0.72

olulu

-0.72

vy

-0.72

atra

-0.72

POSITIVE LOGITS

imental

1.05

ists

0.79

arm

0.74

 license

0.71

 explor

0.71

 Prototype

0.71

 treatments

0.71

 Experimental

0.70

 experimental

0.69

 treatment

0.68

Activations Density 0.018%

mentions of experimental or investigational procedures or studies

terms related to experimental research and studies

No Comments

No Known Activations