INDEX

Explanations

keywords related to tools and tool usage

oai_token-act-pair · gpt-3.5-turbo

references to various tools and utilities used in different contexts

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

 Sons

-0.78

uating

-0.75

oning

-0.72

uates

-0.70

nee

-0.70

otos

-0.67

uated

-0.66

onel

-0.65

 Shal

-0.64

imensional

-0.64

POSITIVE LOGITS

kit

1.16

 tools

1.08

tips

1.03

 tool

0.80

tools

0.78

 Tools

0.77

kat

0.77

belt

0.75

 guiActiveUn

0.75

ets

0.74

Activations Density 0.022%

keywords related to tools and tool usage

references to various tools and utilities used in different contexts

No Comments

No Known Activations