INDEX

Explanations

places or locations

oai_token-act-pair · gpt-3.5-turbo

suffixes and word patterns

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

Austral

-0.61

âĸ¬

-0.59

 GOODMAN

-0.58

 predictor

-0.56

 Mayhem

-0.56

 trump

-0.55

 Reincarn

-0.55

talk

-0.54

Square

-0.53

 ORDER

-0.53

POSITIVE LOGITS

arson

0.89

ffe

0.87

oof

0.77

aga

0.73

acht

0.70

zynski

0.70

edi

0.70

monds

0.67

urat

0.66

heny

0.66

Activations Density 0.376%

places or locations

suffixes and word patterns

No Comments

No Known Activations