INDEX

Explanations

keywords related to tables or structured data within a document

oai_token-act-pair · gpt-3.5-turbo

references to tables and appendices in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

vernment

-0.82

estern

-0.73

=-=-=-=-=-=-=-=-

-0.70

qua

-0.67

 Advocate

-0.66

 cruc

-0.66

 holiest

-0.65

Â¯

-0.65

igious

-0.64

 protective

-0.64

POSITIVE LOGITS

table

1.02

Table

0.96

poons

0.93

TABLE

0.83

 Table

0.83

 TABLE

0.82

cloth

0.82

 table

0.78

 tables

0.77

poon

0.76

Activations Density 0.010%

keywords related to tables or structured data within a document

references to tables and appendices in documents

No Comments

No Known Activations