INDEX

Explanations

references to the name "Hunter" with varying intensities

oai_token-act-pair · gpt-3.5-turbo

mentions of the character "Hunter" 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

raints

-1.00

itutional

-0.83

iment

-0.83

ible

-0.79

ibilities

-0.78

eas

-0.77

alam

-0.76

itution

-0.75

orative

-0.75

orship

-0.74

POSITIVE LOGITS

 Hunter

0.93

sonian

0.81

stown

0.78

stal

0.73

son

0.73

gon

0.70

Hunter

0.68

ball

0.68

 Hunting

0.67

hood

0.67

Activations Density 0.015%

references to the name "Hunter" with varying intensities

mentions of the character "Hunter" in various contexts

No Comments

No Known Activations