INDEX

Explanations

terms related to physical injuries like scars

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of scars and the scars' implications, whether physical or emotional

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

hower

-0.79

£ı

-0.79

ĨĴ

-0.73

ostics

-0.73

gaard

-0.71

ablishment

-0.69

ictionary

-0.67

ullivan

-0.67

 stale

-0.65

eger

-0.64

POSITIVE LOGITS

red

1.02

ring

0.98

lets

0.93

pered

0.93

crow

0.92

fing

0.90

uler

0.89

lett

0.86

abs

0.86

ifiable

0.85

Activations Density 0.021%

terms related to physical injuries like scars

terms related to the concept of scars and the scars' implications, whether physical or emotional

No Comments

No Known Activations