INDEX

Explanations

words related to guards or guarding activities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "guard" 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

BLE

-0.86

 Springs

-0.69

CAST

-0.67

LES

-0.67

ãĥ£

-0.66

MAP

-0.64

KEN

-0.63

sequent

-0.61

MED

-0.61

ilater

-0.60

POSITIVE LOGITS

rail

0.96

 guard

0.86

heed

0.83

ages

0.82

 guarding

0.82

masters

0.79

 guards

0.79

guards

0.78

guard

0.77

llan

0.76

Activations Density 0.026%

words related to guards or guarding activities

instances of the word "guard" in various contexts

No Comments

No Known Activations