INDEX

Explanations

terms related to shapes and physical forms

oai_token-act-pair · gpt-3.5-turbo

mentions of various types and forms of shapes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Mub

-0.84

onte

-0.76

unts

-0.74

aires

-0.70

amily

-0.65

 Countdown

-0.61

arna

-0.61

 Goodman

-0.61

roma

-0.61

ammy

-0.61

POSITIVE LOGITS

 shif

0.97

 shape

0.96

forms

0.89

shape

0.86

 shapes

0.86

ly

0.83

Shape

0.82

liness

0.80

forming

0.77

sheet

0.77

Activations Density 0.038%

terms related to shapes and physical forms

mentions of various types and forms of shapes

No Comments

No Known Activations