INDEX

Explanations

sentence structure patterns related to speaking or reporting

oai_token-act-pair · gpt-3.5-turbo

emphatic expressions and statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Lyme

-0.66

NES

-0.60

 Subject

-0.56

Atk

-0.56

 Hutchinson

-0.56

VM

-0.55

 Vita

-0.55

 Plant

-0.54

 Ranch

-0.54

DIY

-0.54

POSITIVE LOGITS

etheless

1.05

theless

0.98

ulty

0.95

mosp

0.94

zbollah

0.93

govtrack

0.87

ngth

0.85

icularly

0.84

*/(

0.84

etheus

0.83

Activations Density 0.272%

sentence structure patterns related to speaking or reporting

emphatic expressions and statements

No Comments

No Known Activations