INDEX

Explanations

the name "Gore" with varying magnitudes of relevance

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Gore."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

akedown

-0.89

Constructed

-0.81

ivity

-0.77

istically

-0.73

ologically

-0.73

ively

-0.72

uously

-0.72

uing

-0.67

alogue

-0.67

onomic

-0.67

POSITIVE LOGITS

byss

1.34

stein

0.94

pedia

0.89

hound

0.85

tto

0.84

tti

0.84

cki

0.79

 Verb

0.78

boro

0.78

bite

0.77

Activations Density 0.011%

the name "Gore" with varying magnitudes of relevance

mentions of the name "Gore."

No Comments

No Known Activations