INDEX

Explanations

code-related terms and software instructions

oai_token-act-pair · gpt-3.5-turbo

occurrences of numerical values associated with comments or annotations in code

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

issance

-0.81

 delinqu

-0.73

nown

-0.72

 destro

-0.70

eness

-0.70

idon

-0.68

imar

-0.67

vertisement

-0.67

 coffers

-0.67

 laun

-0.67

POSITIVE LOGITS

################################

1.35

########

1.29

define

1.25

################

1.25

DIV

1.14

###

1.14

ERROR

1.07

include

1.04

!/

0.96

endif

0.96

Activations Density 0.015%

code-related terms and software instructions

occurrences of numerical values associated with comments or annotations in code

No Comments

No Known Activations