INDEX

Explanations

locations and directions

oai_token-act-pair · gpt-3.5-turbo

actions related to movement towards locations or objects

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

imon

-0.64

 evolves

-0.61

 compares

-0.61

 versus

-0.61

 ticking

-0.60

 combined

-0.60

:-)

-0.59

 alike

-0.58

 regimes

-0.58

 dealt

-0.57

POSITIVE LOGITS

Ô

0.86

 retrieve

0.74

Ct

0.73

 nearest

0.72

 Elys

0.68

 relieve

0.68

 Nanto

0.67

 pasture

0.66

 collect

0.66

 Glou

0.66

Activations Density 0.175%

locations and directions

actions related to movement towards locations or objects

No Comments

No Known Activations