INDEX

Explanations

phrases related to government policies and regulations

oai_token-act-pair · gpt-3.5-turbo

conjunctions and terms related to various processes and activities

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

ukong

-0.83

ouls

-0.76

atically

-0.74

onymous

-0.74

ulhu

-0.71

hatt

-0.67

omed

-0.67

iazep

-0.67

facebook

-0.67

gyn

-0.67

POSITIVE LOGITS

 processing

1.07

 evaluation

1.05

 dissemination

1.00

 maintenance

0.98

 preparation

0.98

 destruction

0.97

 extermination

0.94

 retrieval

0.94

processing

0.93

 handling

0.93

Activations Density 0.348%

phrases related to government policies and regulations

conjunctions and terms related to various processes and activities

No Comments

No Known Activations