INDEX

Explanations

commands or instructions involving inserting or adding something

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of inserting or adding something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

externalActionCode

-1.02

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.77

ãĥ£

-0.76

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.75

yah

-0.73

byss

-0.71

Â¯Â¯

-0.71

 opio

-0.70

cia

-0.70

rior

-0.66

POSITIVE LOGITS

 inserted

0.86

utions

0.86

 inserts

0.84

 Insert

0.81

Insert

0.81

ional

0.78

 insert

0.78

isions

0.76

aneous

0.75

insert

0.75

Activations Density 0.020%

commands or instructions involving inserting or adding something

words related to the concept of inserting or adding something

No Comments

No Known Activations