INDEX

Explanations

words related to physical appearance, particularly focusing on weight and body shape

oai_token-act-pair · gpt-3.5-turbo

terms related to body size and physical appearance

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

ative

-0.88

iller

-0.88

esian

-0.83

inations

-0.83

enary

-0.80

argon

-0.79

ataka

-0.79

atography

-0.78

ophers

-0.78

endez

-0.77

POSITIVE LOGITS

bum

0.96

LOAD

0.85

 cheeks

0.80

Bey

0.75

 belly

0.74

 Fool

0.70

GROUND

0.70

button

0.70

buck

0.69

poke

0.69

Activations Density 0.054%

words related to physical appearance, particularly focusing on weight and body shape

terms related to body size and physical appearance

No Comments

No Known Activations