INDEX

Explanations

words related to expertise or knowledge in a specific context

oai_token-act-pair · gpt-3.5-turbo

words related to categories or classifications

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

©¶æ

-0.73

icer

-0.70

BUR

-0.69

#$

-0.67

andel

-0.66

tailed

-0.65

[&

-0.64

aldehyde

-0.63

aqu

-0.62

obal

-0.61

POSITIVE LOGITS

 meanwhile

0.87

 âĸº

0.73

geist

0.67

 Senegal

0.67

 however

0.66

 hemisphere

0.65

 notably

0.65

verages

0.64

speaking

0.64

 thankfully

0.63

Activations Density 0.418%

words related to expertise or knowledge in a specific context

words related to categories or classifications

No Comments

No Known Activations