INDEX

Explanations

references to roller coasters

oai_token-act-pair · gpt-3.5-turbo

references to roller coasters

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

itives

-0.76

itutional

-0.73

 Tens

-0.70

ENC

-0.69

itable

-0.67

endment

-0.66

iyah

-0.66

icating

-0.65

inates

-0.64

ENTS

-0.64

POSITIVE LOGITS

 coaster

1.37

 derby

1.11

 roller

1.09

ball

0.99

roller

0.97

 rink

0.95

balls

0.89

boarding

0.89

bike

0.88

whe

0.88

Activations Density 0.021%

references to roller coasters

references to roller coasters

No Comments

No Known Activations