INDEX

Explanations

words or phrases related to planning, strategizing, or preparing for an action

oai_token-act-pair · gpt-3.5-turbo

forms of the word "ning" used in various contexts

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

ublic

-0.83

reon

-0.79

rehensive

-0.77

 Leilan

-0.76

Neg

-0.75

Altern

-0.73

apter

-0.73

Weather

-0.71

irlf

-0.70

ensable

-0.69

POSITIVE LOGITS

ning

1.12

ned

0.90

HAM

0.83

brook

0.81

alties

0.80

ding

0.79

bach

0.74

stocks

0.74

ham

0.74

theless

0.72

Activations Density 0.024%

words or phrases related to planning, strategizing, or preparing for an action

forms of the word "ning" used in various contexts

No Comments

No Known Activations