INDEX

Explanations

code-related terms and descriptions

oai_token-act-pair · gpt-3.5-turbo

technical terminology and concepts related to programming functions and data structures

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

phot

-0.89

clerosis

-0.76

odcast

-0.75

forums

-0.72

staff

-0.72

stru

-0.71

today

-0.70

conduct

-0.70

stre

-0.70

é¾įå

-0.70

POSITIVE LOGITS

 integers

1.09

 JSON

1.05

 integer

1.05

 specified

1.05

UTF

1.03

 tuple

1.03

 recursive

1.02

 initialization

1.02

 strings

1.01

 Python

1.00

Activations Density 0.634%

code-related terms and descriptions

technical terminology and concepts related to programming functions and data structures

No Comments

No Known Activations