INDEX

Explanations

adjectives related to frailty or delicacy

oai_token-act-pair · gpt-3.5-turbo

words related to fragility or delicateness

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ificantly

-0.77

atography

-0.76

orthy

-0.75

urai

-0.75

ibur

-0.75

itative

-0.74

endment

-0.73

eston

-0.73

osate

-0.73

oration

-0.72

POSITIVE LOGITS

 fragile

0.96

 adolesc

0.92

 reefs

0.86

 nerves

0.79

 delicate

0.79

 necks

0.74

 bridges

0.74

 pend

0.73

lings

0.70

 brittle

0.70

Activations Density 0.039%

adjectives related to frailty or delicacy

words related to fragility or delicateness

No Comments

No Known Activations