INDEX

Explanations

names of speculative places or people likely in a singular or proper noun format

oai_token-act-pair · gpt-3.5-turbo

words related to geographical locations or entities

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

======

-0.88

ãĤµ

-0.84

ãĥīãĥ©ãĤ´ãĥ³

-0.79

ãĥ³ãĤ¸

-0.77

ãĥ¼ãĥ³

-0.77

Shar

-0.75

ãĥīãĥ©

-0.73

kson

-0.73

jriwal

-0.70

ttle

-0.70

POSITIVE LOGITS

ragon

0.97

ering

0.96

rive

0.90

orf

0.90

rawn

0.89

erer

0.86

ition

0.84

erm

0.84

iverse

0.84

isl

0.83

Activations Density 0.016%

names of speculative places or people likely in a singular or proper noun format

words related to geographical locations or entities

No Comments

No Known Activations