INDEX

Explanations

abbreviated terms used in a specific geographical region

oai_token-act-pair · gpt-3.5-turbo

references to political parties and their actions or implications

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

ngth

-0.74

 guiActiveUn

-0.70

igraph

-0.69

keleton

-0.67

 portrait

-0.66

 reflection

-0.64

pter

-0.62

 reven

-0.61

 Xperia

-0.61

osures

-0.61

POSITIVE LOGITS

lehem

1.09

pillar

0.89

levard

0.81

mingham

0.80

apest

0.79

aughs

0.74

 Aires

0.73

artisan

0.71

dylib

0.70

jamin

0.70

Activations Density 0.033%

abbreviated terms used in a specific geographical region

references to political parties and their actions or implications

No Comments

No Known Activations