INDEX

Explanations

words related to physical movements or actions of traversing from one point to another

oai_token-act-pair · gpt-3.5-turbo

instances of the word "across."

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

nery

-0.85

FORE

-0.74

nas

-0.67

Parents

-0.66

 Lauder

-0.64

ns

-0.63

juven

-0.61

anza

-0.59

spot

-0.59

Loading

-0.58

POSITIVE LOGITS

roads

1.03

 rooft

0.93

atform

0.91

urst

0.79

 paths

0.77

cedented

0.76

rocal

0.76

arrow

0.73

 platforms

0.72

Ĥª

0.71

Activations Density 0.027%

words related to physical movements or actions of traversing from one point to another

instances of the word "across."

No Comments

No Known Activations