INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals or significant figures in a context-driven narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xit

-0.64

-0.62

ithe

-0.59

phas

-0.57

REE

-0.57

Brew

-0.56

hof

-0.55

 americ

-0.54

 Actual

-0.54

spir

-0.54

POSITIVE LOGITS

notations

0.68

 libel

0.67

vou

0.64

 corrobor

0.64

ict

0.63

 Romeo

0.62

 trusts

0.61

 gossip

0.61

him

0.61

 intervened

0.60

Activations Density 1.329%

proper nouns or names

mentions of specific individuals or significant figures in a context-driven narrative

No Comments

No Known Activations