INDEX

Explanations

technical markers within the text, possibly indicative of formatting or metadata

oai_token-act-pair · gpt-3.5-turbo

numeric values and their associated 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

 favor

-0.76

 favorably

-0.74

 purs

-0.74

hovah

-0.71

©¶æ

-0.71

ĪĴ

-0.68

 honors

-0.68

 behaviors

-0.68

 solic

-0.67

 favored

-0.67

POSITIVE LOGITS

However

1.25

Meanwhile

1.13

Topics

1.11

Speaking

1.09

Writing

1.08

But

1.07

Instead

1.06

Read

1.05

Having

1.04

Asked

1.04

Activations Density 0.490%

technical markers within the text, possibly indicative of formatting or metadata

numeric values and their associated contexts

No Comments

No Known Activations