INDEX

Explanations

descriptions of products or services and their features

oai_token-act-pair · gpt-3.5-turbo

occurrences of the article "a" and the indefinite article "an"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

agents

-0.92

anism

-0.84

Attempts

-0.81

encies

-0.76

evidence

-0.73

Engine

-0.72

votes

-0.72

projects

-0.71

words

-0.70

someone

-0.69

POSITIVE LOGITS

 plethora

1.26

 bunch

1.18

 slew

1.17

lot

1.13

 handful

1.07

 multitude

1.06

 whopping

1.05

 glimpse

0.96

 sizeable

0.95

 sizable

0.94

Activations Density 0.330%

descriptions of products or services and their features

occurrences of the article "a" and the indefinite article "an"

No Comments

No Known Activations