INDEX

Explanations

personal reflections, metaphorical reflections, and literal mirrors in a document

oai_token-act-pair · gpt-3.5-turbo

references to mirrors and the concept of reflection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

--------------------------------------------------------

-0.81

ensable

-0.77

stant

-0.73

iott

-0.73

 Reserve

-0.70

wav

-0.70

cific

-0.70

CVE

-0.70

artney

-0.68

estern

-0.66

POSITIVE LOGITS

ror

0.96

 neuron

0.90

 mirror

0.90

 image

0.84

 pane

0.81

 reflection

0.81

ocular

0.79

 shine

0.77

 gazing

0.76

angelo

0.76

Activations Density 0.036%

personal reflections, metaphorical reflections, and literal mirrors in a document

references to mirrors and the concept of reflection

No Comments

No Known Activations