INDEX

Explanations

phrases related to distance or comparison

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a significant discrepancy from an ideal or expected state

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

emis

-0.78

ysis

-0.72

ptive

-0.67

piracy

-0.66

ulus

-0.66

ription

-0.65

icks

-0.64

ellation

-0.63

iliary

-0.63

 Peel

-0.62

POSITIVE LOGITS

 enough

1.07

thing

0.96

fetched

0.92

enough

0.91

med

0.87

 Enough

0.84

entimes

0.83

zx

0.78

ranging

0.74

itud

0.73

Activations Density 0.021%

phrases related to distance or comparison

phrases indicating a significant discrepancy from an ideal or expected state

No Comments

No Known Activations