INDEX

Explanations

concepts related to making adjustments or modifications

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "tweak" and its variations

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

ONT

-0.74

False

-0.67

 Domain

-0.67

OPA

-0.65

çĦ

-0.63

 Seraph

-0.63

inators

-0.63

inating

-0.61

ZA

-0.60

Ort

-0.59

POSITIVE LOGITS

 tweak

0.97

 tweaks

0.94

Twe

0.84

 tweaking

0.82

 calibr

0.82

hement

0.81

eness

0.81

igger

0.80

ables

0.80

alore

0.76

Activations Density 0.014%

concepts related to making adjustments or modifications

occurrences of the word "tweak" and its variations

No Comments

No Known Activations